Skip to main content
Glama

Find company

find_company
Read-onlyIdempotent

Find a company by name or Swiss UID (CHE-123.456.789); an LEI or ISIN finds the Swiss company that carries it, or a company outside Switzerland that Antevo holds because it owns a Swiss one (a thin file). Returns candidates, each with its entity_id, legal form and seat; no file is opened. Pass the chosen candidate's entity_id to company_file. country is optional. Names find Swiss companies only in this version; a name with another country answers not_covered.

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": {
      "query": "<query>"
    },
    "name": "find_company"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes
countryNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses that multiple candidates come back (so the agent must disambiguate), that no file is opened, and that non-Swiss names yield a `not_covered` response. It does not describe pagination or how many candidates are returned, which is a minor remaining gap given the output schema already covers the response shape.

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?

Content is front-loaded with the identifier formats and the handoff to company_file, and every clause carries real information. The parenthetical 'a thin file' and the quoted `not_covered` token are slightly jargon-heavy, but they are load-bearing rather than filler.

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 two-parameter lookup tool with an output schema, the description supplies what the schema cannot: identifier syntax, multi-candidate semantics, the downstream call, and the coverage limitation. Nothing an agent needs to call it correctly or interpret an empty/`not_covered` result 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?

With 0% schema description coverage, the description carries the full burden and mostly succeeds: `query` accepts a name, Swiss UID, LEI, or ISIN, each with distinct matching behavior, and `country` is flagged as optional with its effect on name lookups (`not_covered`). What `country` does for UID/LEI/ISIN queries is left unstated.

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 names a specific verb (find) and resource (company) and enumerates the accepted identifier types with a literal UID example (CHE-123.456.789), plus LEI/ISIN handling. It explicitly contrasts itself with company_file, so an agent can distinguish the lookup step from the file-retrieval step without opening either schema.

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?

It states the downstream step explicitly ('Pass the chosen candidate's `entity_id` to company_file'), which is the correct alternative to route to. It also gives a concrete when-not: name lookups outside Switzerland return `not_covered` in this version, so the agent knows a name + foreign country is a dead end rather than a valid call.

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.