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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the agent knows this is a read-only search that may return changing results. The description adds that station IDs are used in noaa_climate_fetch_data and returns coverage date fields, but it doesn't disclose any additional behavioral nuances (e.g., pagination behavior, ordering defaults) beyond what the schema and annotations already imply. This is slightly above baseline given the annotations exist.

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 a single dense paragraph but is well-organized: purpose first, then filter list, then the compatibility advice, then common ID formats. No redundant filler; each sentence earns its place. Slightly long but justified by the tool's complexity.

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 an 11-parameter search tool with an output schema, the description covers the key functional aspects: filtering by location/extent/dataset/datatype/date, the returned fields, and the station ID formats used downstream. It omits explicit guidance on pagination (offset/limit) and sorting, but the schema documents those with defaults, and the output schema exists so return types are known. Overall complete for an agent to call 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?

Schema coverage is 100%, so all 11 parameters are documented. The description adds real value by providing concrete examples for locationId ('FIPS:37'), extent ('47.5,-122.4,47.7,-122.1'), datasetId ('GHCND'), and datatypeId (['TMAX','TMIN','PRCP']). It also clarifies that date filters should be combined with datasetId to ensure data exists. This exceeds what the bare schema provides.

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 states a specific verb ('Search for... stations') with a clear resource and lists both the filter dimensions (location, bounding box, dataset, data type) and the return fields (IDs, names, coordinates, elevation, coverage dates). It is immediately distinguishable from siblings like noaa_climate_find_locations (locations) and noaa_climate_get_station (single station detail).

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?

Provides clear context for when to use the tool: when you need to find stations by filters. It gives practical advice ('filter by datasetId and startDate/endDate to ensure compatibility') and explains the relationship to noaa_climate_fetch_data. However, it does not explicitly state when NOT to use it or name alternatives (e.g., noaa_climate_get_station for a specific station).

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