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

With no annotations present, the description carries the full burden and does so thoroughly. It discloses Luhn validation, GDPR-safe legal-entity-only scope, caching behavior, pricing, source frequency, and the meaning of empty results. This is rich behavioral context beyond a simple API call.

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 compact but information-dense. Every sentence adds value: purpose, query pattern, return contents, GDPR note, clean-record signal, source, cache, and price. No filler or redundant restating of the tool name.

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?

Given the tool's moderate complexity (3 params, no output schema), the description is complete: it covers return fields, ordering, source, update frequency, caching, pricing, and the clean-record interpretation. It does not describe error handling for invalid SIRENs, but the Luhn-validation mention partially covers that.

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 0%, so the description must compensate, and it does: siren is explained as required and Luhn-validated with an example, famille is described as an optional filter with a concrete value, and limit is given a numeric range. Minor deduction because the description mentions limit=10 as an example while the schema default is 5, which could cause slight confusion.

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?

The description clearly states the tool retrieves legal announcements from the French BODACC official gazette for a single company identified by SIREN. It distinguishes itself from sibling tools like lookup_company_fr or verify_supplier_fr by focusing on BODACC legal announcements, and the optional 'famille=collective' filter ties directly to insolvency proceedings.

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 description provides clear usage context: when to use it (checking a company's legal announcements by SIREN), the required parameter format, and an optional filter. It also explains that zero announcements for a valid SIREN is a clean-record signal, which guides interpretation. However, it does not explicitly name alternative tools for when this tool should not be used.

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