Open-Meteo — Air Quality Forecast

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, so the description doesn't need to restate these. It adds value by disclosing the data source ('Copernicus CAMS model'), the lack of authentication ('no auth'), and licensing ('Open-Meteo CC BY 4.0'). It also notes the return type ('time-series arrays'), providing useful context. There is no contradiction with annotations, and the added metadata goes beyond what's in the schema.

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 front-loaded with the core action ('Get hourly air quality forecast') and then provides supporting detail (pollutants, use cases, model info). It is reasonably concise, with no filler, and each sentence contributes meaningful information. It covers purpose, parameters implicitly, use cases, and caveats, all in a compact form. It could be slightly shorter, but it's well-structured and effective.

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 has an output schema, so the description need not explain return values. The description covers the essential context: global coverage, forecast horizon, pollutant selection, data source, no auth, and licensing. It mentions the model (Copernicus CAMS) and gives a sense of the output structure ('time-series arrays'). It doesn't address rate limits or error handling, but these are common to many tools and not critical for a read-only forecast API. Overall, it's sufficiently complete for an agent to invoke it 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?

The schema has 100% description coverage for all 5 parameters, so the baseline for this dimension is 3. The description lists the available pollutants and implies forecast range, but it does not add substantive meaning beyond what the schema already provides. For example, it doesn't explain the IANA timezone format or the exact string syntax for pollutants; those are in the schema. The description adds minimal value, so a 3 is appropriate.

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 states the tool's function: 'Get hourly air quality forecast (1–7 days ahead) for any global location.' It identifies the resource (air quality forecast) and the scope (global, 1-7 days). It also enumerates the specific pollutants returned, which distinguishes it from sibling tools like openmeteoaq.air.current (current conditions) and openmeteoaq.air.historical (historical data). The verb 'Get' and resource 'forecast' make the purpose 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?

The description provides clear use-case guidance: 'Useful for trip planning, outdoor event scheduling, or health risk monitoring.' This implicitly tells an agent when to select this tool over others. However, it does not explicitly state when NOT to use it or directly contrast with siblings, though the name and description make the forecast orientation evident. The lack of explicit exclusions is a minor gap, but the context is strong enough to warrant a 4.

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