WMO Official City Forecast

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

Annotations include readOnlyHint=true, openWorldHint=true, idempotentHint=true, which already indicate this is a safe, read-only, idempotent operation. The description adds value beyond annotations by disclosing that data availability may be incomplete (fewer days or none) due to NMHS publication status, which is critical behavioral context not in annotations. It also notes the source (worldweather.wmo.int) and lack of auth requirements, which are useful.

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 about two sentences, front-loads the core purpose, and includes essential usage details (ID discovery, return values, caveats) in a compact, readable form. No fluff, each sentence earns its place, and the structure is efficient for an agent scanning for key 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?

Given the tool has only one parameter, a rich schema, and annotations covering safety, the description is nearly complete. It covers what it returns (min/max temp and condition), the data source, need for ID, and variability. The only minor gap is lack of explicit note on output schema (e.g., date format, units), but with an output schema present, not required. Overall sufficient for correct invocation.

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 description covers 100% for the single parameter 'city_id', but the description adds important semantics: it explains the ID is a WMO city ID, gives an example, and directs to the sibling tool to discover it. This adds meaning beyond the schema's basic type and description, especially guiding the agent on how to obtain a valid ID.

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 retrieves an official 7-day daily forecast for a city, sourced directly from the NMHS, distinguishing it from other weather tools like weather.conditions.forecast or meteostat.observations.daily, and specifies the resource (city), verb (get), and scope (daily, 7-day). It also clarifies it is the government-portal forecast, not a third-party model, which is a distinctive purpose.

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 explicitly instructs to first use the sibling tool 'wmo-weather.city_search' to obtain the required city ID, provides an example (183 for Tokyo), and includes caveats about coverage and update frequency varying by NMHS, with the possibility of fewer days or none. This tells the agent when to use it (for official daily forecasts) and implicitly contrasts with alternatives like noaa.weather.forecast.

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