crop

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

The description implies a destructive state-changing operation by advising 'Checkpoints first', and the checkpoint parameter reinforces this. This directly contradicts the readOnlyHint:true annotation, making the behavioral contract inconsistent. The description itself does not state that it mutates the target image or what else changes.

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?

Two short sentences with the core operation first and no redundant wording. It is appropriately concise and front-loaded.

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?

The rect semantics are present, but the description omits what id refers to, what the tool returns, and the full side-effect picture. The checkpoint hint is useful but does not resolve the ambiguity of which image is being cropped or whether the operation is reversible beyond that checkpoint.

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 description adds meaning for the rect parameter by defining x, y, w, h. However, id is not explained in either the schema or the description, and checkpoint is already documented in the schema. With only 33% schema description coverage, this is only partial compensation.

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 specifies the operation ('Crop') and the target shape ('rect [x, y, w, h]'), so an agent knows what the tool does. It doesn't explicitly say which image or window the crop applies to, and it doesn't distinguish itself from crop_preview or auto_crop, but the rect format gives enough core purpose clarity.

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?

There is no guidance about when to use this tool instead of the many crop/processing siblings such as crop_preview or auto_crop. 'Checkpoints first' is a safety/workflow instruction, not a usage-selection guideline, so the agent is left to infer context.

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