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

With no annotations provided, the description carries the full burden. It richly discloses behavior by enumerating what will be returned (obligations, exemptions, content, duration, average cost, certified organisms, validity, penalties) and the legal grounding. It also clarifies the parameter's informational nature. No side effects or auth details, but this is a read-only informational tool, so this level is sufficient.

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 detailed and well-organized, starting with the main purpose and then listing specific components. It is duplicated in French and English, which adds length without extra substance, but every sentence earns its place by conveying concrete information. Could be more concise by dropping one language version, but still efficient.

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 there is no output schema, the description sufficiently explains the expected return: a comprehensive set of training rules, including exemptions, duration, cost, and penalties, plus the legal basis. For a tool with one optional parameter and moderate complexity, this level of detail is adequate for an agent to understand what the tool does and what it returns.

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 description coverage is 100% for the single parameter, and it already explains that type_etablissement is optional, informational, and provides accepted values. The tool description merely repeats this without adding new meaning, so the baseline score of 3 is appropriate.

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's function: returning mandatory HACCP training legal obligations in French commercial catering. It specifies the exact content (who must train, exemptions, duration, cost, penalties) and legal basis, distinguishing it from sibling tools like get_sanctions_ddpp (sanctions) or get_documents_controle_ddpp (documents). The verb 'Retourne' is specific and the resource is well-defined.

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 provides clear context by scoping the tool to France and commercial catering, and explicitly states that the type_etablissement parameter is optional/informational, implying it works for all category types. However, it does not name alternative tools or explicitly say 'use this instead of X', so it falls short of full guidance.

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