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

Annotations are sparse and mostly negative (readOnlyHint=false, idempotentHint=false), so the description carries some burden. It adds useful operational context with 'Coverage depends on the public sources listed for this endpoint' and the per-call price. It does not elaborate on the implications of the non-read-only/non-idempotent hints, but it does not contradict them.

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?

The core description is one clear sentence followed by useful limitation and pricing notes. However, the 'Use when' line is an exact duplicate of the first sentence, wasting space in a definition that should stay tight.

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?

The presence of an output schema and a self-describing identifier/scope/limit schema make this a fairly simple tool, and the description covers cost and coverage caveats. It is not fully complete, though: an agent navigating the large sibling list still lacks guidance for choosing this over company_fr_competitors, company_fr_compare, or company_fr_benchmark, and 'administratively comparable' is left undefined.

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 description coverage is 0%, and the description gives no parameter-specific guidance for identifier, limit, or scope. It only implies that the identifier refers to a French company; it does not explain the SIREN/SIRET pattern, the meaning of scope values, or the acceptable limit range beyond what the schema already encodes.

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 concrete action and target: 'Finds administratively comparable French companies for later comparison or benchmarking.' The verb and resource are clear. It does not explicitly distinguish this from sibling tools such as company_fr_compare or company_fr_competitors, so it misses the top score.

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?

The 'Use when' section merely repeats the first sentence verbatim rather than adding selection criteria. The 'Avoid when' section is a legal disclaimer rather than a comparative usage guideline, and no sibling alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.