crop_image

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

With no annotations, the description carries the full burden. It discloses the coordinate system, the non-destructive nature via a new image_id, and that the input must be a cached image. It does not detail invalid-region behavior, but the schema covers ordering constraints.

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 operational content is front-loaded and efficient. The trailing benchmark claim about CharXiv is motivational rather than functional, and 'use it liberally' is more style than substance, so it does not fully earn its place.

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 5-parameter tool with a complete input schema, the description covers the when, the coordinate semantics, the source image requirement, and the return behavior. The lack of an output schema is mitigated by explicitly stating that a new image_id is returned.

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 the baseline is 3. The description adds value by explaining the normalized 0..1 bounding-box concept and explicitly stating that (0,0) is top-left and (1,1) is bottom-right, which helps an agent reason about x1/y1/x2/y2.

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 states a specific operation: zoom into a cached image by normalized 0..1 bounding box. It also clearly ties the tool to the render_* workflow by positioning it as the follow-up step for inspecting details like faces, edges, or fillets.

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?

Explicitly says to use after render_* when inspecting a detail, and even encourages liberal use. It does not enumerate when not to use it or name alternative zoom/recrop approaches, but the guidance is clear and actionable.

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