Image Crop

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

Annotations already declare the safety profile (readOnly=false, openWorld=false, destructive=false), and the description adds real context beyond them: the external FFmpeg dependency, the LOCAL_FILE_ACCESS_ROOT scoping, the hash-to-bytes binding caveat, and that large outputs retain metadata/path only. It stops short of detailing failure modes or rate behavior.

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?

Four tight sentences with the purpose front-loaded and the constraints following in priority order. The final sentence's caveat about factual support/synthetic inputs is somewhat tangential but still earns its place as a scope limiter.

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?

An output schema exists, so return values need not be explained, and the description covers prerequisites, path scoping, and caveats. It is nearly complete; only explicit sibling routing is absent.

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 100%, so all four parameters (crop_box, file_path, output_path, include_image) are already documented in the schema. The description adds no syntax or format detail beyond it, so baseline 3 is correct.

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 and resource ('Crop local PNG pixels') and immediately scopes it against inference-based siblings with 'without model inference or provider uploads,' so an agent can distinguish it from image_edit/image_segment without opening the schema.

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 phrase 'without model inference or provider uploads' signals the deterministic-local use case, and 'Requires an independently installed FFmpeg' plus the LOCAL_FILE_ACCESS_ROOT reference give prerequisites. However, it never names an alternative tool or states when-not-to-use it, so routing still requires inference.

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