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

Annotations already mark this as read-only/idempotent, and the description adds meaningful behavioral context: ignored legal forms and accents, homonym disambiguation via postal code, per-request response fields, the fiabilité scale, a safety warning about ambiguous SIRENs, and the fact that it is free without an API key. No contradiction with 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 dense but every sentence adds value: purpose, normalization behavior, disambiguation tip, input format, output format, safety guidance, and cost. It is front-loaded with the core purpose and remains readable without fluff.

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 sparse schema and no output schema, the description is remarkably complete. It explains the exact request payload, response fields and reliability levels, the limitation to 10 companies, a critical user-facing guideline, and operational characteristics like cost and keyless access. No important usage aspect is missing for a tool of this complexity.

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 input schema is extremely sparse, offering only an array of objects with no per-field descriptions. The description fully compensates by specifying the expected object structure ({"nom": str, "code_postal": str?, "ref": str?}), the max batch size, and the per-company response fields, enabling correct invocation and response interpretation.

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 a specific action ('Retrouve le SIREN') and resource ('entreprises françaises'), and it distinguishes itself from siblings like verifier_siret by focusing on resolving names from CRM data to SIREN identifiers, not verifying a provided SIRET.

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?

Provides concrete usage context: when you have company names as written in a CRM, when to include postal code for disambiguation, a batch limit of 10, and the lack of API key. It does not explicitly mention when not to use it or point to alternatives, but the context is clear enough for correct selection.

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