image_crop

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so mutation is disclosed structurally. The description adds the top-left origin rule, but says nothing about the overwrite parameter's effect, what happens when the output path already exists, or whether an out-of-bounds rectangle errors or clips — critical gaps for a destructive file-writing tool.

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, no waste, and the coordinate convention — the most error-prone detail — is front-loaded. It is under-specified rather than bloated.

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 no explanation. For a destructive, 7-parameter file operation, however, the description omits overwrite semantics and bounds/error behavior, leaving meaningful gaps.

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 description coverage is 0%, so the description must compensate. It only clarifies x and y (pixels, top-left origin); width, height, overwrite, input_path and output_path are undocumented anywhere.

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 a rectangle from an image') and adds coordinate semantics. It does not distinguish itself from close siblings like image_resize or image_thumbnail, so the agent must infer which tool transforms geometry vs. scales.

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?

No guidance on when to crop versus resize/thumbnail, and no mention of preconditions such as the crop rectangle having to stay within image bounds. The agent is left to discover failure modes on its own.

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