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

Annotations already disclose read-only, idempotent, non-destructive behavior, so the description's job is to add semantics — and it does, defining the accumulation index as 'how strongly the weather keeps particles near the ground' and warning that it is an estimate rather than a measurement. That pre-empts the main misuse risk (treating the index as a PM2.5 reading), which is genuine added context beyond the annotations.

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?

Two sentences, no filler. The payload enumeration and the index definition come first, and the crucial disambiguation lands last, so an agent can skim and still get the scope right.

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 no output schema and six optional parameters, the description is responsible for telling the agent what comes back, and it lists all five output quantities. It stops short of units, ordering, or how lat/lon versus city selection is resolved, but those gaps are minor for a read-only forecast call.

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 83%, so the baseline is 3: lat, lon, city, lang and country are already documented in the schema. The description only gestures at the forecast horizon with 'the next hours' and never explains that 'hours' is configurable up to 72 — the one undocumented parameter — so it does not meaningfully compensate for that 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 names the resource (a city's next-hours forecast) and enumerates the returned quantities: temperature, wind, humidity, precipitation and a 0–100 pollution accumulation index. It also draws a clear line against a PM2.5 forecast, which implicitly separates it from the get_air_quality sibling, though the sibling is never named.

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 final clause 'A weather estimate, not a PM2.5 forecast' gives an implicit exclusion that routes agents toward get_air_quality for actual pollutant levels. However, there is no explicit when-to-use statement and no mention of get_air_quality_history or search_cities as alternatives, so the routing is left to inference.

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