page_match_image

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

With no annotations, the description carries the full burden, and it does substantial work: it discloses in-page computation, full-grayscale/no-grid-loss behavior, return format, coordinate semantics, caching behavior, and single-fetch behavior for challenge URLs. It does not explicitly assert read-only/side-effect-free status, but the matching operation itself strongly implies a non-destructive read.

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 longer than minimal, but nearly every sentence carries distinct useful information: algorithm, output shape, crop behavior, caching, and use cases. The marketing-style caps ('REAL', 'THE tool') add noise, but the structure is front-loaded and information-dense.

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 6-parameter tool with no output schema and no annotations, the description is notably complete: it provides the return structure, coordinate meaning, algorithm, cache semantics, and intended use cases. It does not specify how many top matches are returned or answer edge cases like no-match, but those are minor gaps for an image-matching tool.

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%, and the description enriches parameter meaning beyond the schema by giving a concrete needle_rect use case (instruction glyph band in a GeeTest pattern) and explaining output coordinates in haystack-image pixels. Not every parameter is expanded, but session_id/page_id are standard context IDs and the schema already documents the crop parameters.

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 opens with a specific operation: multi-scale normalized cross-correlation of a needle against a haystack, and specifies the output as matched needle-center positions. It also names concrete use cases (captcha piece->gap, glyph->character, logo->page), which clearly differentiates it from generic vision or OCR siblings.

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 states 'THE tool for: captcha piece->gap, glyph->character, logo->page,' giving clear when-to-use context. It does not explicitly name excluded alternatives, but the use-case framing is strong enough to route an agent toward this tool for template-matching-style problems.

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