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

With no annotations, the description carries the full burden of behavioral disclosure. It details the validation algorithm (INSEE Luhn rule, La Poste exception), input tolerance (spaces/dots/dashes), return fields, offline/cached computation, and pricing. This is comprehensive and leaves no hidden behavioral surprises.

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 three sentences, each packed with distinct value: usage context, validation rules, and returns/pricing. No fluff or repetition.

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 no output schema, the description explicitly lists return fields (valid, type, siren, nic, rule applied) and covers input, algorithm, caching, and cost. It is fully self-contained for an agent to invoke this 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 has only a bare 'number' string parameter with 0% coverage. The description compensates fully by explaining the expected format (9 or 14 digits), tolerance for separators, and even provides an example value, making parameter usage unambiguous.

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 validates French SIREN/SIRET numbers, with a specific verb ('pre-validation') and resource ('French company numbers'). It also distinguishes itself from sibling validation tools by mentioning SIREN/SIRET and the Sirene API context.

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?

It explains when to use the tool ('before invoicing or costly Sirene API calls') and positions it as a cheap, offline pre-check. However, it does not explicitly contrast it with alternative validation tools like validate_vat_eu or verify_company_eu, so it stops short of full exclusion criteria.

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