crop_drawing

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

The description transparently says it saves a PNG and returns a saved path, which implies a filesystem write. However, the annotations set readOnlyHint=true, indicating the tool does not modify the environment. This is a direct annotation contradiction, so the behavioral transparency score must be 1.

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 three tight sentences with no filler. The core action is front-loaded, parameter constraints are compact, and the limitation/anti-goal statement is placed at the end without waste.

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 crop tool with an output schema, the description covers the essential geometry semantics, scale limits, return value, and a clear statement of non-goals. The main gap is the unexplained autocontrast parameter, but the description is otherwise enough for correct invocation in normal cases.

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?

With 0% schema description coverage, the description must carry parameter meaning, and it does for the most important ones: bbox_px is defined as exact source-image [x0,y0,x1,y1] and scale is bounded to 0.25..12. It also hints at output behavior via the returned PNG path, but it does not explain autocontrast or the output_path default.

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 starts with a specific verb and object: 'Save one model-selected raster drawing region at readable scale.' It also differentiates the tool from analytical siblings by explicitly stating it performs no OCR, feature recognition, or geometry inference, so an agent knows exactly what this tool is for.

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 description clarifies that this is a 'mechanical crop only' and lists what it does not do, which implies when to use it rather than recognition or inference tools. It does not explicitly name alternative sibling tools, but the boundary it draws gives practical usage guidance.

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