Skip to main content
Glama

checkers.fr — entreprises françaises

Comptes annuels

comptes_annuels
Read-onlyIdempotent

Comptes annuels détaillés d’une entreprise : bilan actif et passif, compte de résultat poste par poste (liasse fiscale) et ratios financiers, un bloc par exercice publié et non confidentiel. Pour une analyse financière ou une comparaison sur plusieurs années. Les chiffres clés (chiffre d’affaires, résultat) sont déjà dans fiche_entreprise : n’appelez cet outil que pour le détail, et limitez les années avec annee. Coût : 2 crédits par exercice renvoyé, rien si aucun.

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": {
      "siren": "<siren>"
    },
    "name": "comptes_annuels"
  }
}

Input Schema

NameRequiredDescriptionDefault
anneeNoAnnées de clôture voulues (« [2023, 2024] ») ; toutes si absent.
sirenYesSIREN de l’entreprise, 9 chiffres.

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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description goes beyond them with a cost model ('2 crédits par exercice renvoyé, rien si aucun') and a confidentiality scope ('exercice publié et non confidentiel'), which are exactly the kind of traits annotations cannot express. It does not describe payload size or per-exercice ordering beyond the block statement, so it stops short of a 5.

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?

Two dense sentences, front-loaded with what the tool returns, followed by the routing rule, the narrowing instruction and the cost. No filler and no repetition of the schema.

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?

With no output schema, the description carries the burden of describing returns and does so at a useful level of detail (sections included, one block per exercice). What is missing is minor: nothing on ordering, empty-year behavior beyond cost, or response size, which matters for a potentially large per-exercice payload.

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 schema already defines both parameters and the 'toutes si absent' default for annee. The description adds meaning beyond the schema by tying the annee array to a per-year credit cost and to the detail-only use case, giving the agent a reason to narrow it rather than omit it.

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 resource (comptes annuels) and enumerates its contents — bilan actif/passif, compte de résultat poste par poste (liasse fiscale), ratios — plus the granularity ('un bloc par exercice publié et non confidentiel'). It also explicitly distinguishes itself from the sibling fiche_entreprise, so an agent can separate the two 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 when to use it ('analyse financière ou comparaison sur plusieurs années'), when not to ('les chiffres clés sont déjà dans fiche_entreprise'), and names the alternative explicitly. It also gives an operational instruction to bound the request via annee.

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