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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds meaningful behavior beyond those hints: data source (China National Environmental Monitoring Centre), hourly refresh cadence, province-to-capital resolution, and acceptance of Chinese/English names.

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 dense but well-organized, with the core data payload first, then accepted input formats, then example queries, then sourcing/refresh context. A couple of example queries slightly overlap with schema examples, but the extra natural-language affordances justify their inclusion.

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?

The tool is simple (one required parameter, schema coverage 100%, strong annotations) and the description covers input aliases, output fields, data source, refresh timing, and example use cases. With no output schema present, describing the returned attributes in the description is sufficient and nothing critical 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?

The schema already fully documents the 'city' parameter, so the baseline is 3. The description goes further by clarifying that a province name like 'Guangdong' resolves to Guangzhou and by giving both English and Chinese examples, which adds semantic guidance beyond the raw schema.

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 identifies the operation as retrieving real-time air quality for a Chinese city and enumerates the exact data returned (AQI, PM2.5, PM10, O3, NO2, SO2, CO, rating), so an agent can understand the tool's purpose. It does not explicitly contrast itself with the sibling tools china_air_quality_ranking and china_air_quality_stations, though the resource scope is specific enough to be distinguishable.

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 examples ('what is the air quality in Beijing right now', 'is Shanghai's air safe today') provide clear situational context for when to invoke the tool. It lacks explicit 'when-not-to-use' guidance or pointers to the sibling ranking/station tools, so it is one step below the highest rating.

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