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

Annotations already cover read-only, idempotent, non-destructive, closed-world. The description adds valuable behavioral context: max 5 results, returned fields limited to SIREN/nom/ville, and no Nogogo grade. It doesn't discuss pagination or error behavior, but the return shape is stated when an output schema exists.

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?

Three sentences, each earning its place: purpose, output scope, and exclusions. Front-loaded with the lookup goal, no filler.

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 single-param lookup with rich annotations and an existing output schema, the definition is complete: it states target entity, result cap, returned fields, and unsupported use cases. Nothing essential is missing.

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 100% and the sole query parameter is already documented (nom ou raison sociale d'une seule entreprise). The description restates the single-company constraint, adding marginal value beyond the schema. Baseline 3 for full coverage.

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?

Declares a specific verb (rechercher) and resource (entreprise française), plus the goal (identifier son SIREN). It implicitly distinguishes from the sibling get_nogogo_grade by stating it supplies no Nogogo grade.

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?

Specifies context and scope: lookup by name, capped at 5 results, and explicitly excludes listes, extractions massives, comparaisons, classements. This tells the agent when not to use it and points away from the sibling by denying the grade output.

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