stac_search

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

Despite no annotations, the description transparently discloses key behaviors: results are cached for follow-up operations, return format is JSON sorted by cloud cover or date, and hints field is provided for troubleshooting. It also specifies when parameters are ignored and the default catalog/collection. No contradictions.

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 well-structured with a brief summary, numbered arguments, returns, tips, and an example. It is front-loaded with the purpose, and every sentence adds value. While lengthy, it is not verbose given the 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?

Given the complexity (7 parameters, no output schema, 23 sibling tools), the description is complete: it covers all parameter details, edge cases (e.g., omit date_range for cop-dem-glo-30), typical workflow, caching, and troubleshooting hints. It provides sufficient context for an AI agent to effectively use the tool.

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?

With 0% schema description coverage, the description compensates fully by providing detailed semantics for all 7 parameters: bbox format with example, collection options with resolution and bands, date_range format, max_cloud_cover defaults and exceptions, max_items default, catalog options, and output_mode. It also includes tips and examples.

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 'Search for satellite scenes matching spatial and temporal criteria' and identifies it as 'the primary entry point for finding satellite imagery'. This distinguishes it from siblings like stac_describe_scene and stac_download_bands, which are follow-up operations.

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 provides a typical workflow (stac_search → stac_describe_scene → stac_download_bands), offers tips for specific use cases (e.g., flood mapping, vegetation analysis), and advises when to adjust parameters (e.g., increase max_cloud_cover for cloudy regions, use sentinel-1-grd for SAR). It also notes when certain parameters are ignored (e.g., max_cloud_cover for non-optical collections) and suggests alternatives if zero results.

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