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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds a genuinely non-obvious behavioral rule: no silent fallback to Paris, meaning missing location should surface a question. It does not discuss error paths, data freshness or forecast horizon, so it falls short of a 5.

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?

Four short sentences, front-loaded with the scope constraint, and no filler. The telegraphic style (« question= peut porter la ville ») is slightly cryptic but every sentence carries information.

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?

With an output schema present and full schema coverage, the description only needs to handle routing and behavioral pitfalls — it does so by covering input modes, the no-fallback rule, and the weather-facts-only boundary. The temporal (at) and outdoor_minutes dimensions are left entirely to the schema, which is acceptable but leaves a small gap.

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 coverage is 100%, so baseline is 3. The description adds real meaning beyond the schema: location accepts a city or postal code, lat/lon is an alternative to a place name, and the question field may itself carry the city — nuances not stated in the schema. It still says nothing about at or outdoor_minutes.

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?

« Faits météo seulement » states the resource (weather facts) and implicitly the scope limit, which distinguishes it from siblings like weather_looks and recommend_weather_look that presumably blend weather with outfit advice. There is no explicit verb such as 'retrieve the forecast', but the intended output is unambiguous.

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?

« Ville/CP OU lat+lon » conveys the accepted input modes, and « Pas de repli silencieux sur Paris » gives one concrete rule (ask rather than default). However, no sibling tool is named as an alternative and no explicit when-to-use/when-not-to-use framing is provided.

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