face_detect_liveness

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

Since no annotations are provided, the description must carry the full behavioral transparency burden. It correctly states the classification task (live vs. spoof), which implies a binary decision, but it does not disclose what happens when liveness cannot be determined (e.g., low confidence, ambiguous cases), expected output format/confidence scores, or any security/capture requirements for the image.

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?

A single sentence of moderate length directly conveys the purpose without any fluff. Every word is meaningful and earns its place.

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?

Given the simplicity (1 required parameter, clear binary decision task) and the presence of an output schema, the description provides enough context for basic use. It could be strengthened by noting that the tool outputs a liveness score or binary result, but the output schema presumably covers that. A minor gap is no mention of image requirements (size, format) for reliable liveness detection.

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 100% with only one parameter. The description does not add semantics beyond the schema, but the parameter is self-explanatory (image_url). The output schema is present (indicated by context signals), so the return value semantics are handled there.

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 clearly states the binary classification task (live vs. printed/screen photo), uses the specific verb 'Decide', and identifies the resource as 'face image'. Within the sibling context (which focuses on aesthetic transformations like age change, cartoonize, beautify), this detection tool is easily distinguishable.

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 gives no guidance on when to use this tool vs. alternatives. From the sibling list, a user might wonder when to use face_detect_liveness vs. face_detect_keypoints, but no comparison or context is provided. It does not mention prerequisites (e.g., image quality, lighting conditions) or limitations.

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