stac_preview

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

With no annotations, the description carries full burden. It discloses the return format (preview_url), response modes (json/text), and that not all scenes have thumbnails. It is transparent about the operation being a quick preview, but could mention potential failure mode details (e.g., network issues).

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 intro, details, tips, and example. Each sentence is informative; no waste. Slightly verbose but justified by the tips section. Front-loaded with purpose.

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 2 parameters, no output schema, and many siblings, the description is complete: explains prerequisites, return values, and usage limitations. It covers all necessary context for an AI agent to use the tool effectively.

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%, but the description fully explains both parameters: scene_id as from stac_search, output_mode with default and options. It provides an example, adding semantic clarity well beyond the bare schema.

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 it retrieves a preview/thumbnail URL for a scene, distinguishing it from siblings like stac_download_bands (full band download) and stac_search (scene discovery). It emphasizes speed advantage, giving a specific verb+resource purpose.

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?

It explicitly notes the scene must come from a prior stac_search call, and advises using it for quick visual checks before full downloads. Tips mention checking for errors if no thumbnail exists, providing clear when-to-use and when-not-to-use guidance.

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