Find satellite imagery

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

Given the annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the safety profile is covered. The description adds useful behavioral context beyond that: it explains that scenes are ranked by area coverage, cloud cover, and date, and that each result includes preview, true-colour image, and STAC item links with the data licence. This gives the agent a clear picture of what to expect from the call and how results are prioritized, which is valuable beyond the annotations.

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 two sentences with no fluff. It front-loads the core purpose (finding scenes), then lists supported sources and the ranking/return details. Every clause conveys useful information, and the structure leads with the most important facts, making it easy for an agent to grasp quickly.

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?

With 10 parameters and an output schema present, the description covers the main functionality but is brief. It explains the purpose, supported collections, ranking, and return types, but does not elaborate on parameter interactions (e.g., how radius_km works with lat/lon, the behavior of sort options, or how limit affects results). Given the complexity, some information is left to the schema and the agent's inference, so the description is adequate but not fully comprehensive.

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 coverage is 60%, leaving four parameters (lat, lon, sort, limit) without descriptions. The tool description indirectly clarifies that area can be specified via bbox or lat/lon, and it mentions the date range (implicitly start/end) and collections. However, it does not explain the meaning of sort, limit, or the default behaviors beyond what the schema already provides (e.g., default collection, default max_cloud). The description adds some meaning but does not fully compensate for the undocumented parameters, so a baseline 3 is appropriate.

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 clear verb ('Finds satellite scenes of an area') and specifies the resource (satellite imagery), the area input (bbox or lat/lon), and date range. It also lists the supported collections (Sentinel-2, Landsat, Sentinel-1, NAIP) and what it returns (preview, true-colour image, STAC links). This is specific and distinguishes it from the sibling 'scene_assets', which implies asset-level operations, though it doesn't explicitly name the alternative.

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 states what the tool does but provides no guidance on when to use it versus the sibling tool 'scene_assets' or any other alternative. It does not mention when not to use it, prerequisite conditions, or why one would choose this over another method. The usage is only implied (find imagery), not explicit, and there are no exclusions or conditional recommendations.

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