Fetch one company from the French RNE/INPI registry using its registration number or registry URL; returns name, status, registration date, address, and legal form.
Get one company from the France registry (RNE / INPI) by registration number or registry URL: name, status, registration date, address and legal form. Flat 30 points per successful run.
| Name | Required | Description | Default |
|---|---|---|---|
| company | Yes | Registration number or registry URL. e.g. 552032534 |
Changes observed during successful MCP inspections.
v1.0.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose a valuable behavioral trait in the cost model ('Flat 30 points per successful run'), which structured fields don't convey. It does not cover behavior on invalid/unknown registration numbers, error or empty-result handling, or whether repeated lookups are cached.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero filler: identity and return fields first, the unusual cost caveat second. Nothing is buried and nothing is repeated.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description usefully enumerates the returned attributes (name, status, registration date, address, legal form), which is exactly the gap it needs to fill. With one fully documented parameter and a stated cost model, an agent has enough to invoke this correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema already documents the single 'company' parameter, including an example ('552032534'). The description restates the accepted formats (registration number or registry URL) without adding new syntax, validation rules, or fallback behavior. Baseline 3 applies when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Get one company'), the exact resource and jurisdiction (France registry, RNE / INPI), the input form (registration number or registry URL), and the field set returned. This cleanly separates it from the sibling run_fr_companies_search, which takes no single-identifier lookup.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies you must already hold an identifier (registration number or registry URL), which is a meaningful usage constraint for this tool versus a name search. However, it never explicitly names run_fr_companies_search as the alternative when you only have a company name, which is the single most likely misuse given ~200 sibling lookup tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.