stac_search

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

With no annotations, the description carries the full burden, and it does disclose useful behaviours: no authentication required, place takes precedence over bbox, omitted datetime defaults to recent, cloud filtering only applies when eo:cloud_cover exists, and limit is capped at 10. It says nothing about the response shape, pagination, or failure modes, leaving meaningful gaps for a search tool.

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 opening line and Args block are front-loaded and useful, but the collection example list ('landsat-c2-l2', 'sentinel-2-l1c', ...) is duplicated verbatim between the preamble and the collection arg entry, wasting space in an otherwise tight definition.

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 six-parameter search tool with no annotations, no output schema, and zero schema descriptions, the parameter coverage is good but the description never tells the agent what comes back (item IDs, geometries, assets, thumbnails) or whether results are sorted or paginated. An agent can call it, but cannot predict its response.

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 0%, so the description must compensate, and it largely does: it documents all six parameters including the bbox coordinate order ('lon_min,lat_min,lon_max,lat_max'), datetime format ('YYYY-MM-DD' or 'start/end'), collection default, limit default/max, and the collection-precedence rule for place. Only minor ambiguity, such as what 'recent' means for datetime, keeps it from a 5.

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?

States a specific verb+resource ('STAC検索' of satellite data via AWS Earth Search) and names concrete collections (Sentinel-2, Landsat, NAIP, DEM), which separates it from neighbours like uk_stac_search and copernicus_search. It does not explicitly say why to choose it over those other regional STAC search siblings, so it stops short of full differentiation.

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 illustrative queries ('東京のLandsat画像', '関東のSentinel-2の雲が少ない画像') and points to stac_collections for validating collection IDs, and notes authentication is unnecessary. However it never states when to prefer this over the many sibling search tools (copernicus_search, jaxa_dataset_search, uk_stac_search), leaving usage context implied.

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