MCP tools - TAMTAM

This page documents the Model Context Protocol (MCP) tool surface. Each tool’s input schema is generated directly from the server, so the parameters listed here are exactly what the MCP tools/list handshake exposes to your assistant. 44 tools are registered.

Error behavior

Errors are uniform across every tool:

Invalid arguments (wrong type, malformed payload) return a tool error (isError: true) with a message prefixed invalid arguments:. The call is not billed.
Internal failures return a tool error with a generic message; details are logged server-side and not exposed to the caller.
A tool error is delivered as a normal MCP result with isError: true (not a transport-level failure), so the assistant can read the message and recover.

Parameters not listed as required are optional. Where a default is shown, omitting the parameter applies that default.

`add_companies_to_key_accounts`

Add one or more companies to Key Accounts. This must be done before any deep-research tool can be called on a target company. Costs 1 credit per newly-added company; companies already in Key Accounts are not re-charged. Use a search tool (search_companies_by_name, search_companies_by_filters, etc.) first to obtain LinkedIn IDs. Call skill_research_key_account first to learn the full research workflow and the asynchronous nature of the generated outputs.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_ids`	array<string>	required	—	—	LinkedIn IDs of companies to add to Key Accounts. Resolve via search_companies_by_name first.
`tags`	array<string>	optional	—	—	Optional free-form tags to attach to newly-unlocked companies (e.g. ‘strategic’, ‘renewal-q2’). Omit if no tags.
`tier_level`	number	optional	1 – 3	`1`	Optional priority tier (1-3). Higher = higher priority. Omit if user has no preference (defaults to 1).

`add_companies_to_list`

Add one or more companies to an existing companies list. Use list_companies_lists (or create_companies_list) to obtain the list ID, and a search tool (search_companies_by_name, search_companies_by_filters, etc.) to obtain the companies’ LinkedIn IDs. Companies already in the list are silently ignored.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_ids`	array<string>	required	—	—	LinkedIn IDs of companies to add. Resolve via a search tool first.
`list_id`	string	required	—	—	UUID of the companies list to add companies to.

`add_contacts_to_list`

Add one or more contacts to an existing contacts list. Use list_contacts_lists (or create_contacts_list) to obtain the list ID. Contact IDs that don’t exist or belong to another account are silently skipped and reported back; contacts already in the list are not re-added.

Parameter	Type	Required	Allowed values	Default	Description
`contact_ids`	array<string>	required	—	—	UUIDs of the contacts to add to the list.
`list_id`	string	required	—	—	UUID of the contacts list to add contacts to.

`count_people_search_results`

Count how many people match a set of people-search filters, WITHOUT fetching any profile. Consumes no credits, and takes a few seconds — it is a live provider call, not a lookup. Takes the same structured filters as search_people, so the count describes exactly the search you are about to run. Call it before search_people whenever you are searching inside named companies (especially large ones), whenever you are about to paginate, and whenever your filters are elaborate — that is when a search silently collapses to zero or balloons past what you will read. Act on the result:

0 → the filters are too narrow. Relax and re-count before searching: drop the job-title excludes first, then keep only the core titles, then widen location / company size. Tell the user what you relaxed.
Far larger than what you will fetch → do not run one broad search and read the first page; the ordering is relevance, not seniority, so the person the user wants can sit deep in the tail. Split into narrower searches (one per job-title group, or one per company) and count again.
A workable size → run search_people with the same filters.

WHAT A COUNT CANNOT DO: no count honours seniority bands. Bands are applied to profiles after they are fetched, never to the provider query, so a count taken with a persona that carries them is an upper bound and not the answer. When that is the case the response says so: count_is_upper_bound is true and seniority_bands_ignored lists the bands. Quote it to the user as a ceiling — “at most N, fewer once the seniority bands apply” — never as the number of people they will get. Does not accept prompt or next_cursor: it counts a structured filter set, not a natural-language query or an in-flight search.

Parameter	Type	Required	Allowed values	Default	Description
`canonical_job_titles_excludes_ids`	array<string>	optional	—	—	Canonical LinkedIn job title UUIDs to exclude.
`canonical_job_titles_includes_ids`	array<string>	optional	—	—	Canonical LinkedIn job title UUIDs to include.
`company_headcounts`	array<string>	optional	`A`, `B`, `C`, `D`, `E`, `F`, `G`, `H`, `I`	—	Company headcount band codes: A=self-employed, B=1-10, C=11-50, D=51-200, E=201-500, F=501-1000, G=1001-5000, H=5001-10000, I=10001+.
`company_hq_countries`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes of the company’s headquarters (e.g. [‘FR’,‘US’]).
`company_linkedin_ids`	array<string>	optional	—	—	LinkedIn company IDs to filter by.
`countries`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes of the person’s location (e.g. [‘FR’,‘US’]).
`first_name`	string	optional	—	—	Filter by person’s first name.
`industry_excludes_ids`	array<string>	optional	—	—	Industry UUIDs to exclude from the search.
`industry_includes_ids`	array<string>	optional	—	—	Industry UUIDs to include in the search.
`job_titles_excludes`	array<string>	optional	—	—	Job titles to exclude.
`job_titles_includes`	array<string>	optional	—	—	Job titles to include (e.g. [‘Head of Sales’]).
`last_name`	string	optional	—	—	Filter by person’s last name.
`persona_id`	string	optional	—	—	Count using one of the customer’s saved personas, which supplies the job titles, countries and seniority bands behind it. Get IDs from `list_personas`. Any filter you also pass explicitly overrides the persona’s value for that field. Pass the same persona_id to `search_people` so the count describes the search it precedes. A persona carrying seniority bands makes the count an upper bound (see `count_is_upper_bound` in the response): the bands shrink the search’s results, not the count.
`recently_changed_jobs`	boolean	optional	—	—	Only include people who recently changed jobs.
`seniority_includes`	array<string>	optional	`Owner / Partner`, `CXO`, `Vice President`, `Director`, `Experienced Manager`, `Senior`, `Entry Level`, `In Training`	—	Keep only people whose job title names one of these seniority bands, using Tamtam’s own reading of the title, never a provider’s tag. Anyone whose title carries no seniority signal is KEPT rather than dropped (roughly a quarter of titles), so this narrows without silently discarding people a provider failed to label. Applied to profiles after they are fetched, never to the provider query: it shortens a page instead of searching deeper, it cannot pull a senior person up from rank 300 into page 1, and `count_people_search_results` cannot honour it — a count carrying bands comes back flagged `count_is_upper_bound`. Prefer narrowing job titles when you want fewer, more senior results; use this to enforce a band the user named explicitly. A persona passed via `persona_id` supplies its own bands, and anything you pass here overrides them.

`create_companies_list`

Create a new, empty companies list. Returns the new list’s ID, name, and CreatedAt. Use add_companies_to_list afterwards to populate it with companies (resolve their LinkedIn IDs via a search tool first). The list is assigned to the calling user.

Parameter	Type	Required	Allowed values	Default	Description
`name`	string	required	—	—	Name of the companies list to create.
`tags`	array<string>	optional	—	—	Optional free-form tags to attach to the list (e.g. ‘strategic’, ‘q2-targets’). Omit if no tags.

`create_contacts_list`

Create a new, empty contacts list. Returns the new list’s ID, name, and CreatedAt. Use add_contacts_to_list afterwards to populate it with contacts. The list is assigned to the calling user.

Parameter	Type	Required	Allowed values	Default	Description
`name`	string	required	—	—	Name of the contacts list to create.
`tags`	array<string>	optional	—	—	Optional free-form tags to attach to the list (e.g. ‘champions’, ‘q2-outreach’). Omit if no tags.

`enrich_people`

Enrich people with their professional email addresses and/or phone numbers. Identify people by LinkedIn URL (preferred), or by firstname + lastname + company domain. The domain field is required when enriching email addresses. Runs asynchronously: may return status="PENDING" — follow the next_action field. Call skill_find_people first to learn the recommended workflow. Costs 1 credit per email address and 10 credits per phone number. Maximum 100 people per request.

Parameter	Type	Required	Allowed values	Default	Description
`requests`	array<object>	required	—	—	List of people to enrich.

requests[] fields:

Parameter	Type	Required	Allowed values	Default	Description
`enrich_fields`	array<string>	required	`contact.emails`, `contact.phones`	—	Fields to enrich: ‘contact.emails’, ‘contact.phones’, or both.
`company_name`	string	optional	—	—	Company name (optional, improves accuracy).
`custom`	object	optional	—	—	Optional custom key-value pairs returned with results.
`domain`	string	optional	—	—	Company domain (e.g. ‘tamtam.ai’). Required when enriching email addresses.
`firstname`	string	optional	—	—	Person’s first name.
`lastname`	string	optional	—	—	Person’s last name.
`linkedin_url`	string	optional	—	—	LinkedIn profile URL (optional, improves accuracy).

`extract_profile`

Extract a person’s full LinkedIn profile and create a contact in the Tamtam account. Provide linkedin_url for a direct lookup, or any combination of identity hints (email, first_name, last_name, full_name, job_title, company_name, company_linkedin_id, free_text, context) to find the best matching person. Returns the full profile: name, headline, photo, location, experiences, and contact lists. Call skill_find_people first to learn when to use this vs. search_people. Costs 1 credit.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	optional	—	—	LinkedIn numeric ID of the company (most precise company signal).
`company_name`	string	optional	—	—	Current company name (significantly improves matching accuracy).
`context`	string	optional	—	—	Free-form supplemental context (e.g. meeting titles, CRM notes) used to disambiguate. Not a resolvable signal on its own.
`email`	string	optional	—	—	Email address of the person.
`first_name`	string	optional	—	—	First name.
`free_text`	string	optional	—	—	Loosely-structured input (e.g. ‘find John Doe at Google’ or a CSV row). Parsed automatically into the other fields.
`full_name`	string	optional	—	—	Full name (use when first/last are not separated).
`job_title`	string	optional	—	—	Current job title (improves disambiguation).
`last_name`	string	optional	—	—	Last name.
`linkedin_url`	string	optional	—	—	LinkedIn profile URL (e.g. ‘https://www.linkedin.com/in/john-doe’). When provided, used directly and other fields are ignored.

`get_account_mapping`

Fetch the account mapping for a target company: its parent company (if any) and its subsidiaries. Use this when the user wants to understand the target’s corporate structure, find related entities to approach, or expand the account footprint (e.g. “who owns them?”, “what are their subsidiaries?”, “are they part of a larger group?”). Call skill_research_key_account first to learn when to use this vs. the other research tools.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn numeric ID of the target company (e.g. “104924588”).

`get_account_planning`

Fetch the account planning for a target company (identified by its LinkedIn ID). Account planning gives a structured strategic view of the target: revenue, organizational structure, geographies, competitive landscape, goals & 3-5Y plan, business challenges & risks, strategic priorities, and news & industry trends. Resolve the LinkedIn ID with search_companies_by_name if you do not have it. Call skill_research_key_account first to learn when to use this vs. the other research tools.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn numeric ID of the target company (e.g. “104924588”).

`get_companies_from_list`

Retrieve companies inside a companies list, with custom-criteria column values inlined per company. Paginated. Use list_companies_lists first to discover available list IDs.

Parameter	Type	Required	Allowed values	Default	Description
`list_id`	string	required	—	—	UUID of the companies list to fetch companies from.
`keep_obsolete`	boolean	optional	—	`false`	If true, returns custom-criteria values that are obsolete (criterion definition changed since computation). Default false.
`limit`	number	optional	—	—	Max number of companies to return.
`offset`	number	optional	—	`0`	Pagination offset (default 0).

`get_company_job_changes`

Fetch recent job changes at a target company (identified by its LinkedIn ID). Returns who joined the company (INCOMING), got promoted internally (PROMOTION), or left and where they went (OUTGOING). For large companies the unfiltered result can be long — narrow with change_type when the user’s intent is direction-specific (“who joined?” → INCOMING, “any departures?” → OUTGOING, “any internal promotions?” → PROMOTION) and tighten months_back when only the latest changes matter. Pair with get_company_job_postings for outbound hiring signals and with search_people for live org state. Resolve the LinkedIn ID with search_companies_by_name if you do not have it.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn numeric ID of the target company (e.g. “104924588”).
`change_type`	string	optional	`INCOMING`, `PROMOTION`, `OUTGOING`	—	Optional filter. One of “INCOMING” (joiners), “PROMOTION” (internal moves), “OUTGOING” (leavers). Strongly preferred whenever the user’s question is direction-specific, and especially for large companies where unfiltered results can be long. Omit only when the user explicitly asks for all activity.
`limit`	number	optional	≤ 200	`50`	Maximum number of job changes to return (default 50, max 200).
`months_back`	number	optional	1 – 3	`2`	Number of calendar months back to include (1 = current + previous month, 2 = current + 2 previous months). Defaults to 2. Max is 3.

`get_company_job_postings`

Fetch recent job postings for a target company (identified by its LinkedIn ID). Returns postings ordered by posting date (newest first), with title, city, technologies, and a link to the original listing. Use this to surface hiring signals — team growth, tech-stack changes, geographic expansion, new role types — to inform outreach and meeting preparation. Full job descriptions are omitted by default to keep responses compact; set include_description to true when you need to inspect the body of the role (e.g. responsibilities, requirements). Resolve the LinkedIn ID with search_companies_by_name if you do not have it.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn numeric ID of the target company (e.g. “104924588”).
`include_description`	boolean	optional	—	`false`	If true, include the full job description text for each posting. Defaults to false to keep responses compact. Set to true when you need the body of the role (responsibilities, requirements, etc.).
`limit`	number	optional	≤ 500	`100`	Maximum number of job postings to return (default 100, max 500).
`since`	string	optional	—	—	Return job postings posted since this RFC3339 timestamp (e.g. “2026-04-01T00:00:00Z”). Defaults to 30 days ago. Max lookback is 90 days.

`get_company_news`

Fetch recent news articles for a target company (identified by its LinkedIn ID). Returns articles ordered by publication date (newest first), with key points summarising each article and a per-account relevance assessment (whether the article matters for this customer’s sales opportunities, why, and concrete actionable insights). Use this to surface buying signals, fundraising, leadership changes, product launches, or strategic moves to inform outreach and meeting preparation. Resolve the LinkedIn ID with search_companies_by_name if you do not have it.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn numeric ID of the target company (e.g. “104924588”).
`limit`	number	optional	≤ 200	`50`	Maximum number of news items to return (default 50, max 200).
`relevant_only`	boolean	optional	—	—	If true, only return articles flagged as relevant to this account’s sales opportunities. Defaults to true. Set to false to also include articles whose relevance has not been flagged or assessed.
`since`	string	optional	—	—	Return news published since this RFC3339 timestamp (e.g. “2026-04-01T00:00:00Z”). Defaults to 30 days ago. Max lookback is 90 days.

`get_company_past_discussions`

Refresh and return a human-readable summary of the seller’s past discussions with a target company (identified by its LinkedIn ID): current/past deals, attendee history, engagement highlights, identified pains, objections, next steps, meeting tips, deal health, business case. Triggers an on-demand refresh first when the CRM has newer interactions than the stored summary; idempotent and a no-op when nothing has changed since the last run. Requires the seller’s CRM (HubSpot or Salesforce) to be connected; returns an empty summary when no engagements are recorded. Resolve the LinkedIn ID with search_companies_by_name if you do not have it.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn numeric ID of the target company (e.g. “104924588”).
`max_age_days`	number	optional	—	`30`	Force a refresh when the stored summary is older than this many days. Defaults to 30. Pass a smaller value when you specifically need very fresh data; pass a larger value to skip a refresh.

`get_company_research_answers`

Fetch the answers to the customer’s standing research questions for a specific target company. The set of questions themselves is account-wide (configured by the customer); this tool runs/retrieves their results for one given company. Each entry includes the question name, the question text, the run status, and the answers if available. Use this to get concrete, question-by-question insights about a specific company. Different from get_account_planning (broad strategic sections) and get_seller_questions (info about the customer themselves, not a target). Call skill_research_key_account first to learn when to use this vs. the other research tools.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn numeric ID of the target company (e.g. “104924588”).

`get_contact_list_contacts`

Retrieve all contacts inside a contacts list. Returns each contact’s identity, current experience, status, and the timestamp at which the contact was added to the list. Also returns contact_brief: AI-answered icebreaker questions per contact (may be empty if research has not yet been triggered from the UI for the contact’s company). Use list_contacts_lists first to discover available list IDs.

Parameter	Type	Required	Allowed values	Default	Description
`contacts_list_id`	string	required	—	—	UUID of the contacts list to fetch contacts from.

`get_contact_past_discussions`

Refresh and return a human-readable summary of the seller’s past discussions with a single contact (identified by its Tamtam contact UUID): engagement highlights, key topics, stated pains, objections, interests, sentiment, responsiveness, role signals, relationship history, next steps, talking points, and open questions. Triggers an on-demand refresh first when the CRM has newer interactions than the stored summary; idempotent and a no-op when nothing has changed since the last run. Requires the seller’s CRM (HubSpot or Salesforce) to be connected; returns an empty summary when no engagements are recorded. Resolve the contact UUID via get_contact_list_contacts or get_pipegen_list_leads (the id field).

Parameter	Type	Required	Allowed values	Default	Description
`contact_id`	string	required	—	—	UUID of the contact (the `id` field returned by `get_contact_list_contacts` or `get_pipegen_list_leads`).
`max_age_days`	number	optional	—	`30`	Force a refresh when the stored summary is older than this many days. Defaults to 30. Pass a smaller value when you specifically need very fresh data; pass a larger value to skip a refresh.

`get_contact_research_answers`

Fetch the answers to research questions the customer has already asked about a specific person. Contact-level counterpart to get_company_research_answers, and the one to reach for when the answer differs per person rather than per employer, e.g. which brands someone looks after inside a large group. Read-only. This returns what has already been answered; it never asks a new question, never starts work, and never spends credits. A question nobody has asked about this person is simply absent from the result, and there is no tool here to ask one — that is done by the customer in the app or over the REST API.

Parameter	Type	Required	Allowed values	Default	Description
`contact_id`	string	required	—	—	Tamtam contact UUID, as returned by the people-search and contact-list tools.

`get_deal_meddic`

Fetch the latest MEDDIC qualification snapshot for every CRM deal (HubSpot or Salesforce) linked to a target company (identified by its LinkedIn ID). MEDDIC scores six dimensions (Metrics, Economic Buyer, Decision Criteria, Decision Process, Identify Pain, Champion) on a 0-10 scale, each with bullet points and grounding from CRM engagements. Use this to assess where each open deal stands and what is missing before advancing it. Resolve the LinkedIn ID with search_companies_by_name if you do not have it. MEDDIC is generated on-demand inside Tamtam — if a deal has no snapshot yet, ask the user to generate it from the deal in the app first.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn numeric ID of the target company (e.g. “104924588”).

`get_enrichment_results`

Retrieve results for an enrich_people call that returned status="PENDING". If still PENDING after this call, follow the next_action field to continue polling. Enrichment typically completes within 10 minutes.

Parameter	Type	Required	Allowed values	Default	Description
`request_id`	string	required	—	—	The request_id returned by enrich_people.

`get_lead_scores`

Return the Lead Score for the account’s contacts, max 50 per call. Each contact gets a 0-100 buyer-fit score (higher = better fit). Address each contact by its Tamtam contact_id (the id / contact_id field from get_contact_list_contacts, get_pipegen_list_leads, or search_people) together with the company_linkedin_id the contact currently works at, read from the same result. The score is scoped to that company because a contact with multiple current jobs has one score per company. ALWAYS batch: pass every (contact, company) you need scored in a single call rather than calling once per contact. score null means the pair could not be evaluated (no LinkedIn profile or current experience at that company resolved); score 0 means evaluated but not a fit. If more than 50 pairs are passed, the first 50 are scored and truncated:true + total_requested are returned, so re-call with the rest.

Parameter	Type	Required	Allowed values	Default	Description
`contacts`	array<object>	required	—	—	List of (contact, company) pairs to score. Max 50.

contacts[] fields:

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn company ID the contact currently works at (e.g. “1441”). Read from the same result that yielded the contact_id. The Lead Score is scoped to this company.
`contact_id`	string	required	—	—	Tamtam internal contact UUID (36-char format), from the id / contact_id field of get_contact_list_contacts, get_pipegen_list_leads, or search_people.

`get_pain_hypothesis`

Fetch the pain hypothesis for a target company (identified by its LinkedIn ID). The pain hypothesis gives a fitness score (how well the customer’s offering fits the target), a list of actionable challenges the target likely faces (each with supporting facts from public sources and a suggested solution). Use this to assess fit and prepare targeted outreach or meeting talking points for a specific company. Call skill_research_key_account first to learn when to use this vs. the other research tools.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_id`	string	required	—	—	LinkedIn numeric ID of the target company (e.g. “104924588”).

`get_pipegen_list_leads`

Retrieve all leads inside a prospecting (PipeGen) list. Returns each lead’s identity, current experience, status. Also returns contact_brief: AI-answered icebreaker questions per lead (may be empty if research has not yet been triggered from the UI for the lead’s company). Use list_pipegen_lists first to discover available list IDs.

Parameter	Type	Required	Allowed values	Default	Description
`pipegen_list_id`	string	required	—	—	UUID of the prospecting (PipeGen) list to fetch leads from.

`get_research_results`

Wait for and retrieve research results previously started with research_companies. Polls internally until all companies are computed or a timeout is reached. Returns per-company status (pending, completed, error) and values. If all_completed is false after return, call again to continue waiting.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_ids`	array<string>	required	—	—	LinkedIn IDs of the companies to check results for.
`criteria_id`	string	required	—	—	The criteria_id returned by research_companies.

`get_seller_questions`

Fetch the seller questions and answers for the current customer account. Seller questions gives a comprehensive understanding of the customer as a company: their products, target market, value proposition, business outcomes, pain points, ROI, competitors, USPs, and competitive gaps. Use this when you need to understand the customer’s business in depth to provide relevant and insightful assistance — for example before configurating their account for them or giving strategic advice when the user has not provided enough information. Not needed for tactical assistance (using Tamtam features, finding contact info) where the user’s own description in the conversation is enough. No input parameters.

`get_youtube_video_transcript`

Fetch a YouTube video’s full spoken transcript from its URL (or video ID). Returns the video metadata (title, channel description, length, views, publication date) together with the full transcript text. Use this to brief yourself on a video before a meeting, extract talking points, or feed the transcript into further reasoning (e.g. competitive analysis, executive prep, podcast intelligence). The transcript comes from YouTube’s own subtitles when available, with an audio-transcription fallback otherwise; if neither works the tool returns an error and no credits are charged. Cost scales with video length: 1 credit per minute, minimum 10. A 5-min clip costs 10 credits; a 30-min talk costs 30; a 2h podcast costs 120.

Parameter	Type	Required	Allowed values	Default	Description
`url`	string	required	—	—	YouTube video URL (e.g. “https://www.youtube.com/watch?v=dQw4w9WgXcQ”) or bare video ID.

`list_companies_lists`

List all existing companies lists. Returns each list’s ID, name, tags, assignee, CreatedAt, and UpdatedAt. Results are ordered by UpdatedAt (most recently updated first). Use this to discover available companies lists before performing actions on them. No input parameters.

`list_contacts_lists`

List all existing contacts lists. Returns each list’s ID, name, tags, and assignee. Use this to discover available contacts lists before performing actions on them. No input parameters.

`list_key_accounts`

List the companies the current user has in Key Accounts. Returns each company’s LinkedIn ID, name, domain, LinkedIn slug, HQ country, industry, logo URL, employee count, and the timestamp it was last added/updated in Key Accounts. Use this to discover which companies the user has unlocked for deep research. No input parameters.

`list_personas`

List the customer’s saved personas: their definition of who they sell to. Each persona carries the job titles, countries and seniority bands behind it, so you can see what a persona means and not just its name. Pass a returned id as persona_id to search_people or count_people_search_results instead of retyping those filters — the persona’s definition is what the customer actually maintains, so it stays correct as they edit it. Personas marked criteria_only drive scoring and cannot be searched from. No input parameters.

`list_pipegen_lists`

List all existing prospecting (PipeGen) lists. Returns each list’s ID, name, owner, createdAt, updatedAt, archived state, visibility status, contact count, and whether it was auto-created. Results are ordered by updatedAt (most recently updated first). Use this to discover available prospecting lists before performing actions on them. No input parameters.

`research_companies`

Create a research criteria and compute it on specific companies. Results are computed asynchronously — use get_research_results with the returned criteria_id to poll for completion. Supported criteria types and their required parameters:

‘nbJobOffers’: title_includes (required), title_excludes, countries, posted_at_max_age_days, description_includes, description_excludes, job_seniority_or, employment_statuses_or, job_technology_slug_or
‘membersCount’: job_titles_includes or canonical_job_titles_includes_ids (one required), job_titles_excludes, canonical_job_titles_excludes_ids, countries, country_excludes
‘technologiesBool’: technologies (required, array of slugs) — checks whether a company uses specific software (any category: CRM, marketing, HR, engineering, etc.)
‘keywordSearchCompanyLinkedin’: keywords_includes (required), keywords_excludes
‘lookalikeScores’: linkedin_ids or queries (one required)
‘technologies’: returns all software and apps used by the company — not just engineering tools but also CRMs, marketing automation, HR platforms, analytics, ERP, collaboration tools, and more (detected from job postings, website, and other signals). No extra params needed
‘fundraising’: no extra params needed
‘mau’: no extra params needed (monthly website visits)
‘instagramFollowers’: no extra params needed
‘peopleGrowthLastYear’: no extra params needed Costs 1 credit per company for some criteria types.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_ids`	array<string>	required	—	—	LinkedIn numeric IDs of the companies to research (e.g. [“104924588”]).
`criteria_type`	string	required	`nbJobOffers`, `membersCount`, `technologiesBool`, `keywordSearchCompanyLinkedin`, `lookalikeScores`, `technologies`, `fundraising`, `mau`, `instagramFollowers`, `peopleGrowthLastYear`	—	Type of research to perform.
`name`	string	required	—	—	Human-readable name for this research. Example: ‘Hiring senior engineers’.
`canonical_job_titles_excludes_ids`	array<string>	optional	—	—	For membersCount: canonical job title IDs to exclude.
`canonical_job_titles_includes_ids`	array<string>	optional	—	—	For membersCount: canonical job title IDs to include.
`countries`	array<string>	optional	—	—	For nbJobOffers or membersCount: ISO country codes. Example: [‘US’, ‘FR’].
`country_excludes`	array<string>	optional	—	—	For membersCount: ISO country codes to exclude.
`description_excludes`	array<string>	optional	—	—	For nbJobOffers: keywords that must not appear in the job description.
`description_includes`	array<string>	optional	—	—	For nbJobOffers: keywords that must appear in the job description.
`employment_statuses_or`	array<string>	optional	`full_time`, `part_time`, `temporary`, `internship`, `contract`, `freelance`, `co_founder`, `apprenticeship`, `seasonal`, `volunteer`	—	For nbJobOffers: employment types. Values: ‘full_time’, ‘part_time’, ‘temporary’, ‘internship’, ‘contract’, ‘freelance’, ‘co_founder’, ‘apprenticeship’, ‘seasonal’, ‘volunteer’.
`job_seniority_or`	array<string>	optional	`c_level`, `staff`, `senior`, `mid_level`, `junior`	—	For nbJobOffers: seniority levels. Values: ‘c_level’, ‘staff’, ‘senior’, ‘mid_level’, ‘junior’.
`job_technology_slug_or`	array<string>	optional	—	—	For nbJobOffers: technology slugs to filter by (e.g. ‘react’, ‘kubernetes’).
`job_titles_excludes`	array<string>	optional	—	—	For membersCount: job title keywords to exclude.
`job_titles_includes`	array<string>	optional	—	—	For membersCount: job title keywords to include.
`keywords_excludes`	array<string>	optional	—	—	For keywordSearchCompanyLinkedin: keywords that must not appear.
`keywords_includes`	array<string>	optional	—	—	For keywordSearchCompanyLinkedin: keywords that must appear in the company LinkedIn description.
`linkedin_ids`	array<string>	optional	—	—	For lookalikeScores: LinkedIn numeric IDs of reference companies to compare against (e.g. [“104924588”]).
`posted_at_max_age_days`	number	optional	—	`365`	For nbJobOffers: maximum age of job postings in days. Default: 365.
`queries`	array<string>	optional	—	—	For lookalikeScores: text queries describing the ideal company profile.
`technologies`	array<string>	optional	—	—	For technologiesBool: technology slugs to check. Example: [‘react’, ‘kubernetes’].
`title_excludes`	array<string>	optional	—	—	For nbJobOffers: job title keywords to exclude.
`title_includes`	array<string>	optional	—	—	For nbJobOffers: job title keywords to include. Example: [‘engineer’, ‘developer’].

`search_canonical_job_titles`

Search for canonical job titles by keyword. Returns matching job title IDs and English names. The keyword may be in English, French, Spanish, Italian or German: a localized title resolves to the same canonical concept (e.g. ‘Directeur Général’ finds the same entry as ‘Managing Director’), so search in the language the user wrote rather than translating first. Use this to find valid canonical job title IDs for search_people’s canonical_job_titles_includes_ids / canonical_job_titles_excludes_ids parameters. Call skill_find_people first to learn the recommended workflow.

Parameter	Type	Required	Allowed values	Default	Description
`query`	string	required	—	—	The job title keyword to search for, in any supported language (e.g. ‘CTO’, ‘Head of Sales’, ‘Directeur Commercial’).

`search_companies_by_filters`

Search for companies using advanced filters (keywords, industry, country, company size, founded year, employee count, etc.). Returns matching companies with their LinkedIn ID, name, and details. Call skill_find_companies first to learn how to choose between this, lookalikes, and job_postings search. Default filters from account settings are automatically applied when you don’t specify a filter explicitly. The response includes the true total_count, has_more, and next_offset. PAGINATION — DO NOT STOP AT THE FIRST PAGE when the user wants an exhaustive list: re-call with the SAME filters and offset set to the previous response’s next_offset until has_more is false (bounded to 10000 results total).

Parameter	Type	Required	Allowed values	Default	Description
`company_size`	array<string>	optional	`1-10`, `11-50`, `51-200`, `201-500`, `501-1000`, `1001-5000`, `5001-10000`, `10001+`	—	Employee size ranges. Values: ‘1-10’, ‘11-50’, ‘51-200’, ‘201-500’, ‘501-1000’, ‘1001-5000’, ‘5001-10000’, ‘10001+’.
`countries`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes for company HQ location. Example: [‘US’, ‘FR’, ‘DE’].
`excluded_keywords`	array<string>	optional	—	—	Keywords to exclude from search results. Example: [‘consulting’].
`hq_cities`	array<string>	optional	—	—	HQ city names. Example: [‘Paris’, ‘New York’].
`hq_states`	array<string>	optional	—	—	HQ state or region names. Example: [‘California’, ‘Île-de-France’].
`industries_exclude`	array<string>	optional	—	—	LinkedIn industry names to exclude. Example: [‘Staffing and Recruiting’].
`industries_include`	array<string>	optional	—	—	LinkedIn industry names to include. Example: [‘Computer Software’, ‘Financial Services’].
`keywords`	array<string>	optional	—	—	Keywords to search for in the company profile (name, description, specialties). Example: [‘AI’, ‘machine learning’].
`keywords_logic`	string	optional	`OR`, `AND`	`OR`	How to combine keywords: ‘OR’ matches any keyword (default), ‘AND’ requires all keywords.
`limit`	number	optional	≤ 5000	`100`	Maximum number of results to return per page (default 100, max 5000). Use a high limit (e.g. 5000) when the user wants exhaustive results.
`max_employees`	number	optional	—	—	Maximum number of employees on LinkedIn. Example: 1000.
`max_founded_year`	number	optional	—	—	Maximum year the company was founded. Example: 2023.
`min_employees`	number	optional	—	—	Minimum number of employees on LinkedIn. Example: 50.
`min_founded_year`	number	optional	—	—	Minimum year the company was founded. Example: 2010.
`offset`	number	optional	—	`0`	Number of results to skip, for pagination (default 0). To sweep ALL matches: keep the same filters and re-call with offset set to the previous response’s next_offset until has_more is false. Offset paging is bounded to 10000 results total.

`search_companies_by_job_postings`

Search for companies based on their job postings and hiring activity. Filter by job titles, technologies, funding stage, location, and company size. Returns companies that are actively hiring for matching roles. Returned companies are revealed for the account; revealing only unblurs the company data and does NOT add them to Key Accounts. Costs 1 AI credit per newly-revealed company; companies the account already revealed are not re-charged. Use limit to bound how many companies are returned and revealed per page (default 500, max 500). The response includes a pagination block with has_more and next_offset. PAGINATION — DO NOT STOP AT THE FIRST PAGE when the user wants an exhaustive list: re-call with the SAME filters and offset set to the previous response’s pagination.next_offset until pagination.has_more is false (each page reveals its companies and costs credits). Call skill_find_companies first to learn when to use job_postings search vs. other tools. Default filters from account settings are automatically applied when you don’t specify a filter explicitly.

Parameter	Type	Required	Allowed values	Default	Description
`company_countries`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes for company HQ location. Example: [‘US’, ‘FR’, ‘DE’].
`company_countries_exclude`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes to exclude for company HQ.
`company_description_contains`	array<string>	optional	—	—	Keywords that must ALL appear in the company description (AND logic, every keyword must match). For match-ANY semantics use company_description_pattern_or instead. Example: [‘fintech’, ‘payments’].
`company_description_excludes`	array<string>	optional	—	—	Keywords to exclude from company descriptions. Example: [‘consulting’].
`company_description_pattern_or`	array<string>	optional	—	—	Keywords where ANY match is enough in the company description (OR logic, at least one keyword must match). For match-ALL semantics use company_description_contains instead. Example: [‘ecommerce’, ‘online store’, ‘tienda online’].
`company_tech_slugs_and`	array<string>	optional	—	—	Technology slugs the company must ALL use, AND logic (every slug required). Use only when the full stack must be present. Example: [‘react’, ‘typescript’].
`company_tech_slugs_or`	array<string>	optional	—	—	Technology slugs the company uses, OR logic (match if the company uses ANY of these). Prefer this for most tech searches. Example: [‘prestashop’, ‘woocommerce’, ‘magento’].
`company_type`	string	optional	`recruiting_agency`, `direct_employer`, `all`	`all`	Filter by company type: ‘recruiting_agency’, ‘direct_employer’, or ‘all’ (default). Use ‘direct_employer’ to exclude recruiting agencies.
`funding_stages`	array<string>	optional	`angel`, `convertible_note`, `debt_financing`, `equity_crowdfunding`, `other`, `private_equity`, `seed`, `series_a`, `series_b`, `series_c`, `series_d`, `series_e`, `series_f`, `series_g`, `series_h`, `venture_round_not_specified`, `series_i`, `series_j`, `undisclosed`, `series_unknown`, `pre_seed`, `post_ipo_secondary`, `post_ipo_equity`, `post_ipo_debt`, `non_equity_assistance`, `late_vc`, `initial_coin_offering`, `growth_equity_vc`, `grant`, `early_vc`, `corporate_round`, `secondary_market`, `product_crowdfunding`	—	Funding stages to filter by. Example: [‘seed’, ‘series_a’, ‘series_b’]. Values: angel, convertible_note, debt_financing, equity_crowdfunding, other, private_equity, seed, series_a, series_b, series_c, series_d, series_e, series_f, series_g, series_h, venture_round_not_specified, series_i, series_j, undisclosed, series_unknown, pre_seed, post_ipo_secondary, post_ipo_equity, post_ipo_debt, non_equity_assistance, late_vc, initial_coin_offering, growth_equity_vc, grant, early_vc, corporate_round, secondary_market, product_crowdfunding.
`industry_exclude_ids`	array<string>	optional	—	—	Industry UUIDs to exclude. Use search_industries to find valid IDs.
`industry_ids`	array<string>	optional	—	—	Industry UUIDs to filter by. Use search_industries to find valid IDs.
`job_countries`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes for job location (can differ from company HQ). Example: [‘US’, ‘FR’].
`job_description_contains`	array<string>	optional	—	—	Keywords that must appear in the job description. Example: [‘remote’, ‘senior’].
`job_description_excludes`	array<string>	optional	—	—	Keywords to exclude from job descriptions. Example: [‘clearance required’].
`job_seniority`	array<string>	optional	—	—	Seniority levels. Example: [‘senior’, ‘lead’, ‘manager’].
`job_tech_slugs`	array<string>	optional	—	—	Technology slugs mentioned in job postings (lowercase). Example: [‘python’, ‘kubernetes’, ‘react’].
`job_titles`	array<string>	optional	—	—	Job titles to search for. Example: [‘Data Engineer’, ‘Machine Learning Engineer’].
`job_titles_exclude`	array<string>	optional	—	—	Job titles to exclude from results. Example: [‘Intern’, ‘Trainee’].
`limit`	number	optional	≤ 500	`500`	Maximum number of companies to return and reveal per page (default 500, max 500). Each newly-revealed company costs 1 credit.
`max_employees`	number	optional	—	—	Maximum number of employees. Example: 1000.
`max_funding_usd`	number	optional	—	—	Maximum total funding in USD. Example: 50000000 for under $50M.
`max_revenue_usd`	number	optional	—	—	Maximum annual revenue in USD.
`min_employees`	number	optional	—	—	Minimum number of employees. Example: 50.
`min_funding_usd`	number	optional	—	—	Minimum total funding in USD. Example: 1000000 for $1M+.
`min_revenue_usd`	number	optional	—	—	Minimum annual revenue in USD.
`offset`	number	optional	—	`0`	Number of results to skip, for pagination (default 0). To sweep ALL matches: keep the same filters and re-call with offset set to the previous response’s pagination.next_offset until pagination.has_more is false. Should be a multiple of limit. Each page reveals its companies (costs credits).
`posted_at_max_age_days`	number	optional	—	`90`	Only include job postings from the last N days (default 90). Example: 30 for last month only.
`remote`	boolean	optional	—	—	Filter for remote positions only.

`search_companies_by_lookalikes`

Find companies similar to given reference companies. Uses AI-powered similarity search. You must provide at least one company_linkedin_id. Call skill_find_companies first to learn when to use lookalikes vs. other search tools. Costs 1 credit per call. Default filters from the user / account settings (HQ countries, company sizes, employee-count range) are automatically applied when you don’t specify the corresponding filter explicitly. Passing an explicit value (including an empty array) overrides the default. IMPORTANT: When multiple company_linkedin_ids are passed in the same call, they are merged into ONE combined similarity fingerprint (results are similar to ALL seeds at once, not similar to ANY of them). If the user names several distinct seed companies and wants companies similar to any of them, call this tool once per seed and union the results — do NOT batch them into one call. Only batch multiple IDs when the user explicitly asks for companies similar to the seeds as a group. When fanning out across multiple seeds, dedupe the union by linkedin_id; an overlap across seeds is a strong-fit signal worth surfacing.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_ids`	array<string>	optional	—	—	LinkedIn IDs of reference companies to find lookalikes for. Use search_companies_by_name to find LinkedIn IDs first. Pass ONE seed per call when the user lists multiple distinct seeds; pass multiple only when the user explicitly wants companies similar to the seeds as a group (they will be merged into a combined fingerprint).
`company_size`	array<string>	optional	`1-10`, `11-50`, `51-200`, `201-500`, `501-1000`, `1001-5000`, `5001-10000`, `10001+`	—	Employee size ranges. Values: ‘1-10’, ‘11-50’, ‘51-200’, ‘201-500’, ‘501-1000’, ‘1001-5000’, ‘5001-10000’, ‘10001+’.
`countries`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes to filter by HQ location. Example: [‘US’, ‘FR’].
`limit`	number	optional	≤ 500	`100`	Maximum number of results (default 100, max 500). Higher limits consume the same 1 credit.
`max_employees`	number	optional	—	—	Maximum number of employees on LinkedIn.
`min_employees`	number	optional	—	—	Minimum number of employees on LinkedIn.

`search_companies_by_lookalikes_any`

Find companies similar to ANY of several reference companies (OR semantics). Uses AI-powered similarity search. You must provide at least one company_linkedin_id. Call skill_find_companies first to learn when to use lookalikes vs. other search tools. Costs 1 credit per call. Unlike search_companies_by_lookalikes — which merges all seeds into ONE combined fingerprint (results similar to ALL seeds at once) — this tool runs a separate lookalike search per seed and unions the results. Use it when the user names several distinct seed companies and wants companies similar to ANY of them. Each result reports score (the highest score the company reached across the seeds it matched) and match_count (how many of the input seeds it qualified as a lookalike for). Results are ranked by match_count first, then by score: a company similar to several seeds is a stronger fit. Default filters from the user / account settings (HQ countries, company sizes, employee-count range) are automatically applied when you don’t specify the corresponding filter explicitly. Passing an explicit value (including an empty array) overrides the default.

Parameter	Type	Required	Allowed values	Default	Description
`company_linkedin_ids`	array<string>	optional	—	—	LinkedIn IDs of the reference companies to find lookalikes for (OR). Each is searched independently and the results are unioned. Use search_companies_by_name to find LinkedIn IDs first.
`company_size`	array<string>	optional	`1-10`, `11-50`, `51-200`, `201-500`, `501-1000`, `1001-5000`, `5001-10000`, `10001+`	—	Employee size ranges. Values: ‘1-10’, ‘11-50’, ‘51-200’, ‘201-500’, ‘501-1000’, ‘1001-5000’, ‘5001-10000’, ‘10001+’.
`countries`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes to filter by HQ location. Example: [‘US’, ‘FR’].
`limit`	number	optional	≤ 500	`100`	Maximum number of results (default 100, max 500). Higher limits consume the same 1 credit.
`max_employees`	number	optional	—	—	Maximum number of employees on LinkedIn.
`min_employees`	number	optional	—	—	Minimum number of employees on LinkedIn.

`search_companies_by_name`

Search for companies by name. Returns matching companies with their LinkedIn ID, name, domain, and other details. Use this to find a specific company’s LinkedIn ID or to resolve company names for other tools. Call skill_find_companies first to learn the recommended workflows.

Parameter	Type	Required	Allowed values	Default	Description
`query`	string	required	—	—	The company name (or part of it) to search for.

`search_industries`

Search for industries by keyword. Returns matching industry IDs, names, and hierarchy paths. Use this to find valid industry IDs for search_people and search_companies_by_filters / search_companies_by_job_postings. Call skill_find_people or skill_find_companies first to learn the recommended workflows.

Parameter	Type	Required	Allowed values	Default	Description
`query`	string	required	—	—	The keyword to search for (e.g. ‘fintech’, ‘software’, ‘healthcare’).

`search_people`

Search for people — contacts, leads, prospects, or decision-makers — using advanced filters (job titles, seniority, location, company, industry, and more). Returns up to 25 profiles per page with LinkedIn IDs, job titles, companies, and locations. The response also includes total_count (total matches available across all pages) on the first page. Call skill_find_people first to learn how to use this tool effectively. Recommended: use the prompt parameter with a natural-language query (e.g. ‘CTOs at fintech startups in France’) — job titles, seniority, industries, countries, and other filters are automatically extracted from it. Alternatively, use the structured filter fields for precise control when you already have exact IDs. To find valid IDs for structured filters, use search_canonical_job_titles and search_industries. Pass next_cursor from a previous response to fetch the next page (re-call this same tool). Costs 1 credit per profile returned. PAGINATION DEFAULT — DO NOT STOP AT 25: Most people-search requests like ‘find software engineers in healthcare startups in Paris’ or ‘find marketing leaders at fintech companies’ are implicitly asking for a comprehensive list, NOT just 25 results. Stopping at the first page silently is a poor outcome. After the first page, if has_more is true, follow this decision rule:

If the user’s request clearly implies wanting many/all/exhaustive results (broad discovery, building a list, prospecting, ‘find me X’, ‘who are the X’, ‘extract contacts’, persona-based searches): keep paginating by re-calling search_people with the returned next_cursor until has_more is false OR you have collected a reasonable working set (e.g. ~100-200 results), then ask the user if they want to continue. Mention the credit cost.
If the user explicitly requested a specific small number (e.g. ‘find me 10 CTOs’, ‘give me a few examples’): respect that number and stop.
If intent is ambiguous regarding scale: after the first page, proactively ask the user how many results they want (e.g. ‘I found a first batch of 25 out of <total_count> total matches. Do you want me to load more? Each additional page of 25 costs 25 credits.’). Do not silently stop.

ALWAYS surface to the user the total_count returned in the response, so they know how many matches exist before deciding to paginate. SENIORITY IS NOT IN total_count: seniority bands — whether you pass seniority_includes or inherit them from a persona — are applied to the profiles this call fetched, never to the provider query, so total_count describes the match set before they apply. When dropped_by_seniority is present, that many people were removed from this page by the bands — the page being shorter than 25 is not a shortage of matches. Say “N matches, of which these are the ones inside the seniority bands” rather than presenting total_count as what the user will receive.

Parameter	Type	Required	Allowed values	Default	Description
`canonical_job_titles_excludes_ids`	array<string>	optional	—	—	Canonical LinkedIn job title UUIDs to exclude.
`canonical_job_titles_includes_ids`	array<string>	optional	—	—	Canonical LinkedIn job title UUIDs to include.
`company_headcounts`	array<string>	optional	`A`, `B`, `C`, `D`, `E`, `F`, `G`, `H`, `I`	—	Company headcount band codes: A=self-employed, B=1-10, C=11-50, D=51-200, E=201-500, F=501-1000, G=1001-5000, H=5001-10000, I=10001+.
`company_hq_countries`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes of the company’s headquarters (e.g. [‘FR’,‘US’]).
`company_linkedin_ids`	array<string>	optional	—	—	LinkedIn company IDs to filter by.
`countries`	array<string>	optional	—	—	ISO 3166-1 alpha-2 country codes of the person’s location (e.g. [‘FR’,‘US’]).
`first_name`	string	optional	—	—	Filter by person’s first name.
`industry_excludes_ids`	array<string>	optional	—	—	Industry UUIDs to exclude from the search.
`industry_includes_ids`	array<string>	optional	—	—	Industry UUIDs to include in the search.
`job_titles_excludes`	array<string>	optional	—	—	Job titles to exclude.
`job_titles_includes`	array<string>	optional	—	—	Job titles to include (e.g. [‘Head of Sales’]).
`last_name`	string	optional	—	—	Filter by person’s last name.
`next_cursor`	string	optional	—	—	Opaque pagination token returned by the previous response’s next_cursor. Pass it back unchanged to fetch the next page. Invalid or expired cursors return an error inviting a fresh search.
`persona_id`	string	optional	—	—	Search using one of the customer’s saved personas, which supplies the job titles, countries and seniority bands behind it. Get IDs from `list_personas`. Prefer this over retyping a persona’s filters: the definition is what the customer maintains. Any filter you also pass explicitly overrides the persona’s value for that field, so combine it with `company_linkedin_ids` to search a persona within specific companies. Mutually exclusive with `prompt`. One persona per call — to cover several, call once per persona.
`prompt`	string	optional	—	—	Natural-language search query. Mutually exclusive with structured filters.
`recently_changed_jobs`	boolean	optional	—	—	Only include people who recently changed jobs.
`seniority_includes`	array<string>	optional	`Owner / Partner`, `CXO`, `Vice President`, `Director`, `Experienced Manager`, `Senior`, `Entry Level`, `In Training`	—	Keep only people whose job title names one of these seniority bands, using Tamtam’s own reading of the title, never a provider’s tag. Anyone whose title carries no seniority signal is KEPT rather than dropped (roughly a quarter of titles), so this narrows without silently discarding people a provider failed to label. Applied to profiles after they are fetched, never to the provider query: it shortens a page instead of searching deeper, it cannot pull a senior person up from rank 300 into page 1, and `count_people_search_results` cannot honour it — a count carrying bands comes back flagged `count_is_upper_bound`. Prefer narrowing job titles when you want fewer, more senior results; use this to enforce a band the user named explicitly. A persona passed via `persona_id` supplies its own bands, and anything you pass here overrides them.

`skill_find_companies`

IMPORTANT: Call this BEFORE any company search or discovery task. Returns expert knowledge on which company search tools to use, how to combine them, and how to get the best results. No parameters needed. No input parameters.

`skill_find_people`

IMPORTANT: Call this BEFORE any task involving finding people, contacts, leads, or prospects — whether by search filters, name, LinkedIn URL, or email. Returns expert knowledge on which people-related tools to use, how to combine them, and how to interpret filters. No parameters needed. No input parameters.

`skill_research_key_account`

IMPORTANT: Call this BEFORE researching a specific target company in Key Accounts — their strategy, pains, fit, standing research answers, corporate structure, or recent news and buying signals. Returns expert knowledge on which research tools to use, the Key Accounts pre-requisite, and how to handle the asynchronous nature of research outputs. No parameters needed. No input parameters.

​Error behavior

​add_companies_to_key_accounts

​add_companies_to_list

​add_contacts_to_list

​count_people_search_results

​create_companies_list

​create_contacts_list

​enrich_people

​extract_profile

​get_account_mapping

​get_account_planning

​get_companies_from_list

​get_company_job_changes

​get_company_job_postings

​get_company_news

​get_company_past_discussions

​get_company_research_answers

​get_contact_list_contacts

​get_contact_past_discussions

​get_contact_research_answers

​get_deal_meddic

​get_enrichment_results

​get_lead_scores

​get_pain_hypothesis

​get_pipegen_list_leads

​get_research_results

​get_seller_questions

​get_youtube_video_transcript

​list_companies_lists

​list_contacts_lists

​list_key_accounts

​list_personas

​list_pipegen_lists

​research_companies

​search_canonical_job_titles

​search_companies_by_filters

​search_companies_by_job_postings

​search_companies_by_lookalikes

​search_companies_by_lookalikes_any

​search_companies_by_name

​search_industries

​search_people

​skill_find_companies

​skill_find_people

​skill_research_key_account