Skip to main content
Glama

French company briefing for an AI

get_french_company_briefing
Read-only

LLM-ready briefing on a French company (SIREN), returned as Markdown text to read or paste as is: identity without officers, filed accounts over three years with their reliability, BODACC insolvency notices, commercial-court decisions and public contracts counted and dated, each block with its status, age and coverage. Written by code from official registers, no model text; legal entities only (a sole proprietorship answers 400, never charged). The text opens with its instruction and ends with its source line: copy it verbatim. Paid via x402 ($0.05 in USDC or EURC).

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": "get_french_company_briefing"
  }
}

Input Schema

NameRequiredDescriptionDefault
sirenYes9-digit SIREN
langueNofr or en; default: the API key account's language, else fr
api_keyNoOptional Sirenic API key (srn_live_…) to pay with prepaid credits instead of x402, with no wallet needed. Get one at https://api.sirenic.eu/compte?utm_source=api&utm_campaign=mcp. Ignored when x_payment is provided (the signed payment wins). On insufficient balance the tool returns a credits error, not an x402 quote. Each key has a daily spending cap (Paris time, 100 EUR unless set from 1 to 2000 EUR in the account): a call that would exceed it returns the plafond_cle_atteint error (HTTP 429), nothing charged, until midnight Paris time.
x_paymentNoOptional signed x402 PAYMENT-SIGNATURE header value. Omit to receive the payment quote.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / api_key / description
      Previous value: -"Optional Sirenic API key (srn_live_…) to pay with prepaid credits instead of x402, with no wallet needed. Get one at https://api.sirenic.eu/compte?utm_source=api&utm_campaign=mcp. Ignored when x_payment is provided (the signed payment wins). On insufficient balance the tool returns a credits error, not an x402 quote."New value: +"Optional Sirenic API key (srn_live_…) to pay with prepaid credits instead of x402, with no wallet needed. Get one at https://api.sirenic.eu/compte?utm_source=api&utm_campaign=mcp. Ignored when x_payment is provided (the signed payment wins). On insufficient balance the tool returns a credits error, not an x402 quote. Each key has a daily spending cap (Paris time, 100 EUR unless set from 1 to 2000 EUR in the account): a call that would exceed it returns the plafond_cle_atteint error (HTTP 429), nothing charged, until midnight Paris time."
  2. Changed1 schema field changed
    • removedInput schema / additionalProperties
      Removed value: -false
  3. Added

TDQS

A3.9/5.0
Behavior4/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses that the text is code-generated from official registers with no model text, that it opens with an instruction and closes with a source line that must be copied verbatim, that non-legal-entity input returns HTTP 400 and is never charged, and the x402 pricing ($0.05 USDC/EURC). It does not state typical latency or whether results are cached, but the payment, error and output-shape behavior is substantively covered and nothing contradicts the annotations.

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 purpose and content blocks, then constraints, then output contract and pricing — a sensible order with dense but purposeful sentences. The 'copy it verbatim' instruction and the pricing clause earn their place, though the single long sentence is heavy and could be split for easier scanning.

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?

For a read-only, single-identifier tool with no output schema, the description is nearly sufficient: it defines output format (Markdown), the content blocks and their status/age/coverage metadata, the verbatim-copy contract, and payment mechanics. What is missing is the returned size/shape expectation (e.g., length or truncation) and any note on how it differs from the aggregate intelligence sibling.

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 description coverage is 100%, so the schema already documents siren, langue, api_key (including the daily cap and plafond_cle_atteint error) and x_payment. The description adds only the SIREN-scoping and the 400-on-non-legal-entity rule; it says nothing new about the language or payment parameters. Baseline 3 is correct when the schema carries the parameter semantics.

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+resource (LLM-ready briefing on a French company identified by SIREN) and enumerates the exact content blocks: identity without officers, three years of filed accounts with reliability, BODACC insolvency notices, court decisions and public contracts. The 'briefing' framing plus the enumerated contents distinguish it from the many narrower siblings like get_french_company_financials or get_french_company_court_decisions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the description makes clear this is the aggregate 'read or paste as is' briefing, which implicitly tells the agent to prefer it over stitching individual endpoints, and it explicitly excludes legal entities other than companies (sole proprietorships get a 400). However, it never names an alternative tool or states a when-not condition versus get_french_company_intelligence or the per-domain endpoints.

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.