Skip to main content
Glama

Search companies

search_companies
Read-only

[Ids in: none. Ids out: companies[].companyId: company id.] Find companies by BUYING SIGNALS and firmographics — hiring now, fast-growing headcount, revenue band, new leadership, and/or recently funded — optionally scoped by industry, HQ location, and size. FREE (no credits). Returns each company's name, companyId, industry, and size. Combine signals to sharpen: hiring, growingTeamMinPct, revenue and size are ALL required together (e.g. hiring:true + recentFunding:true = hiring AND just raised). LinkedIn can't require recentFunding AND recentLeadershipChange in one search, so asking for both runs each separately and lists companies that have both first — every row then carries signals:[…] and the result says how many have both. The next step is to reach people there: search_people_sales_navigator with companyIds:[the returned companyId values] plus seniorities (and changedJobs / postedOnLinkedIn for timing), or find_decision_makers("") for one company (those pull rows and cost credits). Runs on HeyReagent's shared search database — no account needed. (Note: filtering by which SOFTWARE a company uses is not available on the current data tier.)

Input Schema

NameRequiredDescriptionDefault
limitNoMax companies to return (1–100, default 20). Use 100 to feed the most companies to search_people_sales_navigator via companyIds.
hiringNoOnly companies with open job posts right now (hiring signal).
locationsNoCompany HQ locations, e.g. ["United States"].
headcountsNoCompany size bands. Valid: self-employed, 1-10, 11-50, 51-200, 201-500, 501-1000, 1001-5000, 5001-10000, 10001+.
industriesNoCompany industries, e.g. ["Software","Financial Services"].
recentFundingNoOnly companies with a recent funding event (same as list_funding_signals).
revenueCurrencyNoCurrency for the revenue band (default USD).
growingTeamMinPctNoMinimum headcount-growth percent, e.g. 20 = teams that grew ≥20%.
maxRevenueMillionsNoMaximum annual revenue in millions (same brackets).
minRevenueMillionsNoMinimum annual revenue in millions (e.g. 10 = $10M+). LinkedIn uses fixed brackets (0, 0.2, 1, 2.5, 5, 10, 20, 50, 100, 500, 1000); other values widen to the nearest one. Revenue is LinkedIn's estimate — companies without one are left out.
recentLeadershipChangeNoOnly companies with a recent senior-leadership change (new-boss signal).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already cover readOnly/destructive/openWorld. The description adds real operational value: the AND semantics of combining signals, the LinkedIn limitation on recentFunding+recentLeadershipChange and the two-pass union behavior with signals:[…] output. But it doesn't disclose output format beyond fields listed, or any pagination/rate behavior. Solid context beyond annotations but not rich.

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?

Front-loads the I/O contract and the core purpose, then layers semantics and next steps. Some redundancy across the signal listing and the combination rules, but every sentence carries information relevant to correct invocation.

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?

Given 11 parameters, zero required, and no output schema, the description does a good job explaining filter combination semantics, the LinkedIn limitation, the cost model, and the natural next step. It doesn't need to explain return format (no output schema) but a brief note on how results are ordered/limited would close the remaining gap.

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

Parameters3/5

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

Schema coverage is 100% and each parameter is documented in the schema, so the description mainly restates the signal list. The 'ALL required together' AND-semantics note and the revenue-bracket example in the description add meaning beyond the raw schema, keeping it at baseline 3 rather than higher.

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 (find) and resource (companies) and enumerates the buying-signal/firmographic filters that distinguish it from generic company lookups. The 'FREE (no credits)' framing and the explicit contrast with credit-costing follow-ups further sharpens its niche against siblings like search_linkedin_companies.

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?

Clearly states what it does and routes to the next step (search_people_sales_navigator with companyIds, or find_decision_makers). However, it doesn't explicitly contrast with the very similar sibling search_linkedin_sales_navigator_companies or search_linkedin_companies, so the agent can't be sure which company-search to pick without opening their schemas.

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.