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

Beyond annotations (idempotentHint=true, readOnlyHint=false), the description discloses costing behavior, quota debiting rules, pending/asynchronous behavior, retry timing, token validity, and deliverability semantics. It also explains legal responsibilities and the prohibition on rebuilding files, adding substantial context the annotations cannot convey.

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 long but every sentence adds non-redundant value, and it is organized into clear sections (cost, unit usage, deliverability, speed, responsibility). The main purpose is front-loaded, and the format makes the operational rules easy for an agent to parse.

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 complexity—asynchronous retrieval, quota semantics, error reasons, legal obligations, and conditional parameters—the description covers all necessary operational aspects. The presence of an output schema means return-value details do not need to be restated, and 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?

Although the schema already covers all parameters at 100%, the description adds critical behavioral meaning: last_name must match exactly what get_directors returned or the user pays twice; retrieval_token must be used alone; siren is required except when a token is provided. This goes well beyond the schema's basic descriptions.

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 names the exact verb and resource: 'Revele l'email PROFESSIONNEL d'un dirigeant identifie (apres get_directors)'. It clearly differentiates from sibling tools by anchoring to get_directors and stating it is a single-contact, unit-level operation, not a batch or search tool.

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 and when-not-to-use guidance: after get_directors, paid plans only, no looping over lists, don't retry when email=null with reason=not_found or rejected_by_verification, and how to use retrieval_token for pending results. It even names the quota and hourly-limit consequences of misuse.

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