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 covered. The description adds the behavioral note that weather is not yet handled and that the tool should be chained with recommend_weather_look. It does not disclose what happens with missing optional parameters or how the classification is returned, but the output schema exists and the annotations carry the main behavioral burden.

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 short and front-loaded with the main purpose, followed by a limitation and a chaining instruction. Every sentence earns its place, though the French phrasing is slightly informal and the parameter mapping could be clearer.

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 has 5 parameters, 0% schema coverage, and an output schema, the description provides the core purpose and a chaining hint but does not explain the role of each parameter or the expected output. It is adequate for a simple classification tool but incomplete for an agent that needs to fill all parameters 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?

Schema description coverage is 0%, so the description must compensate for the five parameters. It mentions 'créneau, marche, pièce, ville' as classification dimensions, which loosely maps to at, piece, and occasion, but it does not explain the meaning of 'question' or 'transport', nor how the optional parameters interact. The description adds some semantic context but leaves most parameters underspecified.

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 states a specific verb ('classe') and resource ('une demande'), and gives concrete examples of circumstances (dîner, bureau, mariage, week-end) plus the classification dimensions (créneau, marche, pièce, ville). It is clear what the tool does, though it does not explicitly differentiate it from sibling tools beyond the mention of recommend_weather_look.

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 a clear context: classify a request into categories, and explicitly says 'Pas encore de météo' (no weather yet) and 'Enchaîne avec recommend_weather_look' (follow up with recommend_weather_look). This provides a usage flow and an exclusion, though it does not mention when to use alternatives like recommend_look or get_weather_context.

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