Skip to main content
Glama

Find a company

company_lookup
Read-onlyIdempotent

Resolve a ticker, CIK, FinancialMD id or company name to the company FinancialMD covers, so later calls can use a stable identifier. Identifiers (ticker:AAPL, cik:320193, fmd_...) resolve directly and return the profile with meta.company showing what matched; a free-text name searches the directory and returns candidates with their ids, tickers and listings. Use this first when you are not sure of the ticker, or when a ticker is ambiguous across exchanges (ticker:AAPL.XNAS pins the venue). Issuers on EU and UK regulated markets that do not file with the SEC are covered too: they have no CIK, each candidate carries registry "esef" and an lei, and later calls take lei: or the fmd_id. Statements and filings work for them, in the reporting currency; ownership, prices, events and segments answer not_covered.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

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

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of periods or items to return (default 10, at most 50).
queryYesTicker, "cik:<n>", "lei:<LEI>", "fmd_<id>", or a company name such as "Apple".
countryNoOptional ISO 3166-1 alpha-2 filter for name searches.
exchangeNoOptional exchange MIC filter for name searches (for example XNAS, XNYS).

Output Schema

NameRequiredDescriptionDefault
dataNoFor an identifier: the company profile. For a name: { items: [{ fmd_id, cik, name, country, registry, lei, reporting_template, status, primary_ticker, primary_mic, available_datasets }], next_cursor }.
metaNoRequest metadata: request_id, as_of, company resolution, coverage, pipeline_version, licence, terms, proof_base.
errorNoPresent only on isError results: the API error code and message plus remedy hints.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / query / description
      Previous value: -"Ticker, \"cik:<n>\", \"fmd_<id>\", or a company name such as \"Apple\"."New value: +"Ticker, \"cik:<n>\", \"lei:<LEI>\", \"fmd_<id>\", or a company name such as \"Apple\"."
    • changedOutput schema / properties / data / description
      Previous value: -"For an identifier: the company profile. For a name: { items: [{ fmd_id, cik, name, country, reporting_template, status, primary_ticker, primary_mic, available_datasets }], next_cursor }."New value: +"For an identifier: the company profile. For a name: { items: [{ fmd_id, cik, name, country, registry, lei, reporting_template, status, primary_ticker, primary_mic, available_datasets }], next_cursor }."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare the read-only, idempotent, closed-world profile. The description goes well beyond that: identifier queries return a profile with meta.company showing what matched, name searches return candidates with ids, tickers and listings, and EU/UK ESEF issuers carry registry "esef" and an lei instead of a CIK. It even spells out which downstream capabilities answer not_covered for those issuers, which is exactly the kind of behavioral edge case the annotations cannot convey.

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?

Four densely packed sentences with the core purpose front-loaded and the identifier-vs-name split immediately after. Every sentence carries information, though the ESEF coverage sentence is long and could be split for faster scanning.

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?

For a four-parameter resolver with an output schema, this covers everything an agent needs: input form, return shape, ambiguity handling and coverage boundaries including what downstream tools will refuse. Nothing required in order to call it correctly 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 baseline is 3. The description earns above that by documenting resolution syntax the schema only partially shows: the ticker: prefix, the venue suffix form (ticker:AAPL.XNAS), lei:<LEI> for non-SEC issuers, and the fact that a bare free-text string is treated as a name search. The limit, country and exchange parameters are left to the schema, which is acceptable.

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?

The description opens with a specific verb and resource ('Resolve a ticker, CIK, FinancialMD id or company name to the company FinancialMD covers') and states the goal of producing a stable identifier for later calls. That distinguishes it from sibling lookup tools such as identifiers and identifier_xref without the agent needing to open a schema.

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 use-first rule ('Use this first when you are not sure of the ticker') and a specific ambiguous case ('ticker:AAPL.XNAS pins the venue'). It also explains the fork between direct identifier resolution and free-text directory search. No sibling alternative is named as such, so it stops short of a full when-not comparison.

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