Skip to main content
Glama

Match a company list to the registers

companies_match

Matches a list of companies (a CSV or Excel file in the store, or rows) to the registers: each row by its registry number, or by name with its city counting in its favour, in its country's register (GLEIF where there is none). It runs in the background within the registers' pace (a few hundred rows a minute; slower for countries only GLEIF covers): the reply is 202 with a call_id; follow it with account_get_call, or wait for the companies.matched event. The result: counts, a sample and a results file with the list's columns and each match (id, name, score, city, status, industry, founded, LEI). Only clear matches count; close calls come back ambiguous with candidates, free. The call holds $0.01 a row (max_rows) and charges only the rows matched. Costs $0.01 per row matched; nothing if none are found.

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": "companies_match"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe results file's name.
rowsNo
columnsNoWhich of the list's columns holds what, where its headers are unusual, e.g. {"name": "Firma", "city": "Sitz"}.
countryNoFor rows without a country column, e.g. DE.
file_idNoA CSV or .xlsx list in the file store, with a header row.
max_rowsNoAt least the list's rows; the call holds $0.01 for each.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: asynchronous background execution with a 202 + call_id, follow-up via account_get_call or the companies.matched event, throughput of a few hundred rows a minute (slower for GLEIF-only countries), cost of $0.01 per matched row with a per-row hold and no charge for unmatched or ambiguous rows. This is exactly the behavioral context the readOnlyHint=false / openWorldHint=true 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?

Front-loaded with the core action and packed with useful detail, but it is one dense block and the pricing rule is stated three times ($0.01 a row, holds $0.01, costs $0.01 per row matched), which is redundant.

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 complex async, nested-schema tool with no output schema, the description covers the response shape (counts, sample, results file with the source columns plus id/name/score/city/status/industry/founded/LEI), the polling/event path, and the billing model. An agent has everything needed to call and follow up.

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 83%, so the baseline is 3; the description adds real meaning beyond the schema by explaining that rows are matched by registry number or by name with city weighting, that max_rows sizes the $0.01/row hold, and that country covers rows lacking a country column. It largely restates file_id/columns details already in the schema, keeping it below a 5.

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: matching a list of companies (from a file or rows) to official registers, by registry number or by name plus city, with GLEIF as fallback. This is clearly a bulk-matching tool, distinguishable from single-entity siblings like companies_get, companies_search or lookup_company.

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?

The scenario is clear: bulk list matching, providing either file_id or rows, with columns/country resolving ambiguous headers. It does not, however, name alternatives (e.g. lookup_company for a single company) or state when not to use it, so the agent must infer routing from the batch framing.

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