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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description reinforces 'Aucune donnée n'est modifiée' and adds concrete context: the data source (recherche-entreprises.api.gouv.fr), the geographic scope (France), and the fact that it returns official public data. This goes beyond 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 efficiently written with each sentence contributing meaningful guidance: when to use, what it returns, safety confirmation, and exclusion. It is front-loaded with the purpose and avoids unnecessary detail.

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?

For a one-parameter tool with rich annotations and no output schema, the description fully covers the necessary context: purpose, data source, return content, non-destructive behavior, non-usage cases, and geographic scope. The agent has all needed information to select and invoke 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 provides 100% coverage for the single parameter 'siret', including pattern, length constraints, and a clear description of allowed SIRET/SIREN formats. The tool description adds no extra parameter syntax or semantics beyond what the schema already documents, so a baseline score of 3 is appropriate.

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's purpose: verifying the reliability of a French company using a SIRET/SIREN number via official public data. It specifies the return fields (raison sociale, adresse, statut) and explicitly distinguishes from the search tool used for finding providers.

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 gives explicit when-to-use guidance: 'Utilise cet outil quand l'utilisateur veut vérifier la fiabilité d'une entreprise française' and provides a clear exclusion: 'N'utilise PAS cet outil pour rechercher des prestataires (search).' This directly addresses alternatives among siblings.

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