Skip to main content
Glama

LinkedIn People Search

linkedin_people_search

[Acquire · 5 credits] Search LinkedIn people. Filter by company, title, location, or free-text keywords. Costs 5 credits per page of 25 (map_constellation's built-in lead search is billed at a bundled 1 credit instead, a deliberate discount). Each person comes back with current title, company, company id, start date and location. To list the people at one company, pass its LinkedIn company URL or numeric id as company and walk page while truncated is true. Results are saved to people with their current position, so get_outreach_path can route to them (pass a result's person_id as target_person_id).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "linkedin_people_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoResults page, 25 people per page (default 1). 5 credits per page not already cached.
titleNoCurrent title filter (e.g. 'Director'). Comma-separate several (e.g. 'SDR,Account Executive').
companyNoCurrent company. Pass a LinkedIn company URL (https://www.linkedin.com/company/acme) or a numeric LinkedIn company ID (e.g. '1441', the `id` linkedin_company_info and linkedin_company_search return) for an exact match; comma-separate several. A plain name is matched loosely and can return people from other companies, so prefer the URL or ID.
refreshNoBypass the cache and re-run the search live (costs 5 credits). Default false: a previously-fetched result is returned free, with how long ago it was retrieved.
keywordsNoFree-text search (e.g. 'data engineer fintech')
locationNoLocation filter (e.g. 'New York')

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / company / description
      Previous value: -"Current company. Pass a LinkedIn company URL (https://www.linkedin.com/company/acme) or a numeric LinkedIn company ID (e.g. '1441', the `id` linkedin_company_search returns) for an exact match; comma-separate several. A plain name is matched loosely and can return people from other companies, so prefer the URL or ID."New value: +"Current company. Pass a LinkedIn company URL (https://www.linkedin.com/company/acme) or a numeric LinkedIn company ID (e.g. '1441', the `id` linkedin_company_info and linkedin_company_search return) for an exact match; comma-separate several. A plain name is matched loosely and can return people from other companies, so prefer the URL or ID."
  2. Changed3 schema fields changed
    • changedInput schema / properties / company / description
      Previous value: -"Current company name or LinkedIn slug"New value: +"Current company. Pass a LinkedIn company URL (https://www.linkedin.com/company/acme) or a numeric LinkedIn company ID (e.g. '1441', the `id` linkedin_company_search returns) for an exact match; comma-separate several. A plain name is matched loosely and can return people from other companies, so prefer the URL or ID."
    • addedInput schema / properties / page
      Added value: +{
      +  "description": "Results page, 25 people per page (default 1). 5 credits per page not already cached.",
      +  "maximum": 100,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / title / description
      Previous value: -"Current title filter (e.g. 'Director')"New value: +"Current title filter (e.g. 'Director'). Comma-separate several (e.g. 'SDR,Account Executive')."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only flag openWorldHint and non-read-only/non-idempotent, but the description explains the credit cost (5 per page of 25), the cache behavior and what `refresh` bypasses, and the fact that results persist to `people` — which explains why readOnlyHint is false. It also lists exactly what each person record contains, so the agent knows the payoff of a call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Cost is front-loaded in brackets and the rest proceeds from search → filtering → pagination → downstream use, which is a logical order. The parenthetical about map_constellation's discount is somewhat long, though it does earn its place as a cost comparison.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description enumerates the returned per-person fields and the pagination termination condition, and it explains caching and downstream linkage. Nothing an agent needs to call this correctly or interpret the response is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already defines every parameter including the company URL-vs-name tradeoff. The description adds value mainly by tying `page` to the `truncated` flag as a pagination loop and by framing `refresh` as a cost decision, which is slightly beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Search LinkedIn people") plus the filter dimensions (company, title, location, keywords). It also distinguishes itself from the sibling alternative by noting that map_constellation's built-in lead search is a different, discounted path.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use routing: pass a company URL or numeric id and walk `page` while `truncated` is true to enumerate one company's people, and pass a result's `person_id` to get_outreach_path for outreach. It also names the alternative (map_constellation's bundled 1-credit lead search) so the agent can make a cost-aware choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources