stac_search

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

No annotations are provided, so the description carries the full burden. It does disclose the zero-credential/no-auth behavior and, in the Returns line, the response shape (JSON of scenes, dates, cloud cover, asset keys). But for an external network tool it omits explicit disclosure of outbound network dependency, latency, rate limits, and failure behavior - exactly the context an agent needs before invoking a third-party API.

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?

Well-structured with a front-loaded one-sentence purpose, a terse zero-config note, then clearly labeled Args and Returns sections. The detail in Args is justified for a six-parameter external API tool, and every section earns its place without fluff.

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 a 6-parameter external STAC search with an output schema, the description covers purpose, auth model, all parameter semantics, and return format - the essentials for correct invocation. It falls short only on operational disclosures (error handling, rate limits, latency) that would round out full completeness.

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 description coverage is 0% (properties carry only titles, no descriptions), so the description must compensate - and it does. The Args section documents all six parameters with formats, examples, and coordinate systems (e.g., bbox in WGS84, datetime_range RFC3339 with examples, max_cloud_cover 0-100). Minor gaps: bbox doesn't state it needs exactly 4 numbers and collections isn't cross-referenced to list_supported_collections for valid IDs.

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 opens with a specific verb-resource pair ('Search free STAC catalogs for available satellite scenes') and names the three filtering criteria (spatial, temporal, cloud), which clearly distinguishes it from siblings like list_supported_collections (list only) and download_copernicus_granule (download vs search). No ambiguity about what this tool does.

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 'Zero-config: Queries public STAC endpoints with zero credentials or API keys required' note implicitly tells an agent this is the right tool for public, credential-free data access and implies credentialed data belongs elsewhere. However, it never names alternatives or gives explicit when-to-use / when-not-to-use guidance against siblings like query_nasa_opera or query_spatial_sql, leaving routing partially to inference.

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