page_contrast

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

With no annotations, the description carries the full behavioral burden. It discloses the algorithm, output value range (0 = flat, 9 = strong edge), supported element types, and the network cost ('one fetch per challenge'). It does not state whether the tool is read-only, but the algorithmic description strongly implies it is a pure analysis operation.

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 sentences deliver the algorithm, use cases, output scale, accepted element types, and cost, with the key purpose front-loaded. The phrasing is somewhat dramatic ('HIGH-PASS VISION', 'native tool born from solving GeeTest'), but no sentence is pure filler.

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 description covers purpose, algorithm, output scale, and supported elements, but no output schema exists, so the return format is under-specified—it is unclear whether the result is a JSON matrix, per-cell values, or a visual grid. Additional details about how grid dimensions map to output and error behavior would make it more complete.

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 67%; the described parameters (ref, grid_h, grid_w, blur_radius) have schema descriptions with defaults. The tool description adds context about the grid values and what ref refers to, but it does not go beyond the schema for parameter semantics. The two undocumented parameters are standard session/page identifiers, so the gap is minor.

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—computing a local-contrast grid via |gray - gaussian_blur|—and a clear resource: an element's image from canvas, img, or background-image. It differentiates itself through the explicit high-pass vision concept and concrete use cases (captcha, watermarks, hidden strokes), though it does not explicitly name sibling tools for comparison.

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?

It gives clear usage context: use this tool when content blends into a background and needs to be made visible, with examples like captcha characters, watermarks, and hidden strokes. It also scopes applicable element types (canvas / img / background-image), implying when it should be used. However, it does not explicitly contrast with alternatives like page_pixels or page_vision.

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