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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds that results are paginated and filtered by SIRET prefix, which is useful. However, it does not disclose pagination limits, default ordering, or whether inactive partners are included when actifs_only is false, leaving some behavioral gaps. With annotations covering the main safety aspects, a score of 3 is appropriate.

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 two sentences plus an example, all highly relevant. Every piece serves a purpose: enumerating output fields, mentioning pagination and filtering, and giving a use case. No wasted words.

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 read-only list tool with good annotations and a clear schema (5 parameters, no nested objects, no output schema needed), the description covers the main intent, filtering, and pagination. It is slightly lacking in details about the default behavior of actifs_only and the meaning of offset, but overall sufficient for an agent to use it correctly in most queries.

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 description coverage is only 40% (two of five parameters have descriptions: numero and siret_prefix). The tool description adds context about the SIRET/SIREN filter and the example, but does not explain limit, offset, or actifs_only beyond what the schema provides (defaults and types). Given the low coverage, the description does not fully compensate, but partially helps with the filter parameter. Baseline adjusted downward slightly for the gap.

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 explicitly states the tool lists training organisms habilitated on a certification, specifying the data returned (name, SIRET, role former/evaluer/both, state, dates) and provides a concrete example query. This clearly differentiates it from sibling tools like search_certifications or check_habilitation.

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 mentions pagination and filtering by SIRET/SIREN prefix, offering guidance on how to refine queries. However, it does not explicitly state when NOT to use it (e.g., for checking validity of a single partner, which would use check_validity or check_habilitation), or provide alternatives among siblings.

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