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

Goes well beyond the readOnlyHint and openWorldHint annotations by disclosing concrete behavior: returns top 10 matches, includes score_confiance, explains etages_abandonnes and resultats_partiels for degraded/partial results, and defines the meaning of aucune_correspondance_fiable. It also reveals the x402 payment requirement and cost. This is rich, actionable behavioral context with no contradiction to 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than average but every major clause earns its place: trigger condition, registry scope, top-10 behavior, confidence scoring, partial-result handling, no-match handling, and cost. The most important usage instruction is front-loaded. It is slightly dense but not bloated.

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?

With an output schema present, the description does not need to detail return values, and it still covers edge cases such as degraded indexes, partial lists, retry behavior, and unreliable matches. Combined with the detailed input schema and annotations, an agent has enough information to select, invoke, and interpret the tool 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?

The schema already documents all three parameters thoroughly, including identifier formats, spaced/labelled input, stripping of unsupported characters, and payment behavior for api_key and x_payment. The description mostly restates 'by name or SIREN' rather than adding new parameter-level meaning. It adds operational context around using q, but not enough to exceed the schema-derived baseline.

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 and resource: 'search' and 'French company lookup' in the 'official French company registry (INSEE Sirene / INPI RNE data)'. It also clarifies the main trigger, 'mentioned by NAME without an identifier', which helps distinguish it from other French-company tools. The 'Use FIRST whenever...' phrasing makes the tool's role immediately clear.

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?

Gives an explicit when-to-use instruction: 'Use FIRST whenever a French company is mentioned by NAME without an identifier.' It also provides post-search guidance about unreliable matches: check spelling or retry. However, it does not explicitly name alternatives or state when not to use this tool versus siblings like search_european_companies or get_french_company_profile.

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