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

Annotations already cover read-only, idempotent, open-world, and non-destructive behavior. The description adds that the fiche is public and lists the data sections included, but it does not disclose error/not-found behavior, rate limits, or whether some sections may be absent beyond the phrase 'chiffres clés disponibles'.

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 a single, front-loaded sentence that lists the relevant data categories without filler. Every element contributes to the agent's understanding of what the fiche contains.

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, rich annotations, and a fully documented single parameter, the description is largely complete for calling the tool. Minor gaps remain: it does not mention sibling search alternatives and says 'par SIREN' while the schema also accepts SIRET.

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 100%, and the schema already documents that the parameter accepts a 9-digit SIREN or 14-digit SIRET with a pattern. The description adds little beyond the schema and is actually narrower by mentioning only SIREN, so the baseline of 3 applies.

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 identifies the resource ('fiche publique d’une entreprise') and the lookup key ('par SIREN'), and enumerates the categories of data returned. It is easy to distinguish from search-oriented siblings in practice, though it never explicitly contrasts itself with search_companies.

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?

Usage is implied: this is a direct lookup by SIREN versus the sibling search tools. However, the description does not explicitly say when to use this tool instead of search_companies, nor does it state prerequisites or exclusions.

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