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

Annotations only cover the read-only/open-world safety profile; the description adds genuinely new behavior: the values are forecasts not measurements, computed by Atmo Réunion, on a 1–6 scale, broken down per pollutant. It also states handling rules for the amateur-sensor field (present Atmo's index first, always say sensors are uncalibrated, never compare to a threshold or infer health conclusions), which is exactly the kind of constraint an agent could not infer elsewhere.

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 key distinction (forecast, not measurement) is front-loaded in the first sentence, followed by the sensor caveat and then usage examples. Dense but well ordered; the parenthetical scale and the repeated no-location note are slightly redundant against the schema, keeping it off a 5.

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 single-optional-parameter read tool with no output schema, the description supplies everything an agent needs: what the number means, that it is predictive, what sub-fields exist (sous-indice par polluant, capteurs_amateurs), and how to frame the amateur-sensor data responsibly. Nothing material is missing.

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% and the single parameter already documents accepted place forms (commune, plage, quartier, cirque, sommet, coordinates) and the empty-equals-whole-island default. The description restates the commune granularity and the no-location default but adds no format or resolution detail beyond the schema, so baseline 3 applies.

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?

Names a specific resource (qualité de l'air à La Réunion, par commune) and a specific data product (indice ATMO du jour et du lendemain), and explicitly distinguishes it from a measurement: "une PRÉVISION calculée par Atmo Réunion et pas une mesure". That contrast also separates it from monitoring-style siblings like qualite_eau or meteo_actuelle.

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?

Gives three concrete example user phrasings ("l'air est pollué à Saint-Louis ?", "je peux faire du sport dehors ?") that make the trigger conditions obvious, plus an explicit default ("Sans lieu : toute l'île"). It stops short of naming alternatives or when-not-to-use cases, so it is clear context rather than full routing guidance.

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