Compare two faces

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

With annotations covering only safety hints (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description adds real behavioral context the annotations cannot: exact credit pricing per input combination (186/93/93), the best-face selection rule, and null similarity when a side has no face. It omits auth/permission requirements and error conditions, which keeps it from a 5.

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?

Front-loaded with the operation and its return contract, then inputs, then cost. Every sentence carries information; the three-case credit sentence is slightly verbose but the pricing per combination is genuinely decision-relevant.

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?

There is no output schema, and the description compensates by naming the returned fields (face_found, similarity, match, threshold) and their null semantics. It leaves the threshold's origin and default unexplained, and says nothing about failure modes beyond a missing face, which is the main remaining gap for a paid comparison call.

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 baseline is 3, but the description adds meaning the schema does not: each side is one of three mutually exclusive forms (public URL, CDN key, or 512-number embedding). That explains why all seven parameters are optional — the caller picks one form per side — which the schema alone leaves ambiguous.

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?

States a specific verb and resource: 'Check whether two images (or embeddings) show the same person', plus the key qualifier that it uses the best face on each side. An agent can distinguish this from search_faces, but the description never names or contrasts that sibling explicitly, so differentiation is inferred rather than stated.

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?

Usage context is implied by the operation itself (verify a 1:1 identity match) and the credit cost breakdown gives an economic reason to prefer embeddings, but there is no explicit when-to-use / when-not-to-use guidance and no mention of search_faces as the alternative for one-to-many lookups.

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