face_detect_keypoints

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It mentions the return of 90+ keypoints but omits important details such as rate limits, authentication requirements, image format/size constraints, behavior when no faces are found, or error handling. The transparency is adequate but has clear gaps.

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 extremely concise: one sentence for the core purpose followed by a bullet list of use cases. Every word adds value, with no redundancy or fluff. The structure is well-organized and front-loaded.

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 that an output schema exists (the tool has output schema: true) and the description covers the primary purpose and usage scenarios, the description is largely complete. It lacks details on edge cases (e.g., no faces, unsupported images) but the output schema likely documents the return structure. Overall, it provides sufficient context for an agent to decide when and how to invoke the 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 100%, so the descriptions in the schema already document all parameters (e.g., mode, image_url, face_model_version, need_rotate_detection). The tool description does not add new parameter-level meaning beyond what the schema provides, making a baseline score of 3 appropriate.

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 tool detects faces and returns 90+ keypoints per face, with a specific verb and resource. It distinguishes from sibling tools (e.g., face_swap, face_beautify) by emphasizing raw landmark coordinates for downstream tasks like alignment or animation, which no sibling offers.

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 provides explicit use cases: 'raw landmark coordinates for downstream alignment / animation' and 'count or locate faces.' It does not explicitly state when not to use the tool or mention alternatives, but the context (sibling tools) makes it inferential. A near-perfect score is withheld due to the lack of exclusion guidance.

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