Skip to main content
Glama

List a company's people

list_company_people
Destructive

Use this when the user wants the people who work at one specific company, optionally narrowed by people filters such as seniority or department. Send the company by name, domain or LinkedIn URL. Returns one page of up to 25 people; for the next page, send the same company and filters with the page's next cursor. People never carry an email address or a phone number. Costs $0.001 per person returned, charged to the organization's balance; a company nothing matches answers not_found and is free. Calling again with the same arguments charges again.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "company": "<company>"
    },
    "name": "list_company_people"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoPeople per page, up to 25. The page's most possible cost, `limit` times $0.001, is held from your balance first.
cursorNoThe `pagination.nextCursor` of the page before. Send it with the same search, as the `filters` the first page answered with.
detailNoHow much of each row to return. `short` (the default) leaves out the long fields; `full` returns every field, so ask for few rows with it.short
companyYesThe company, by `name`, website `domain` or `linkedinUrl`. Only the most precise of the values sent is looked up: the LinkedIn URL, then the domain, then the name.
filtersNoPeople filters that narrow the company's people, such as seniority or department, with the values the people filters list.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag openWorldHint, non-idempotence, and a destructive hint, and the description adds real context on top: a per-person price of $0.001 charged to the organization's balance, a hold based on limit, not_found being free, and the warning that repeat calls with identical arguments charge again — which corroborates idempotentHint=false. It also discloses an output constraint (no email or phone on people), though it never explains what the destructive hint actually destroys beyond balance drawdown.

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

Conciseness5/5

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

The description is front-loaded with the triggering condition, then moves through input form, page shape, output limits, and pricing in short declarative sentences. Every sentence carries operational information — pagination, cost, absent fields, free not_found — with no filler or restatement of the title.

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

Completeness4/5

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

For a five-parameter, nested-object, open-world tool with no output schema, it covers the essentials: how to identify the company, how to paginate, what a page contains, which fields are absent, and what it costs. It does not address behavior when multiple companies match an identifier, or which filter keys are valid beyond pointing at the people filters list.

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 already 100%, so the baseline is 3, but the description adds meaning the schema does not: the company object can be supplied by name, domain, or LinkedIn URL, and the cursor must be paired with the same company and filters as the prior page. It also caps the page size at 25 people and ties limit to cost, which clarifies the tradeoff behind the limit parameter. Filter vocabulary is delegated to the people filters list rather than defined here.

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

Purpose4/5

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

The description opens with a specific verb and resource: 'the people who work at one specific company,' which separates it from a broad people search by scoping results to a single employer. It also names the narrowing mechanism (people filters such as seniority or department) and the accepted company identifiers. It does not name search_people or find_company explicitly, so the sibling routing is inferred rather than stated.

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

Usage Guidelines4/5

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

It gives a clear triggering condition ('when the user wants the people who work at one specific company') and explains the pagination workflow: resend the same company and filters with the page's next cursor. It does not spell out when to prefer this over search_people or how to obtain a company ID first, so alternatives are implied by the 'one specific company' framing rather than enumerated.

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