Register a selfie

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

Goes well beyond the annotations by disclosing cost (93 credits), the quality gate thresholds (det_score < 0.6, under 24 px) that cause an HTTP 422 and non-storage, and the no-face outcome. One wrinkle: the description says a retry with the same idempotency_key 'returns the original point_id', while the schema says such retries get a 409 duplicate_request_already_processed — a minor internal inconsistency about what actually comes back.

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 tight sentences, front-loaded with purpose then return values then failure modes then cost. The idempotency sentence partially duplicates the idempotency_key schema description, which is the only real redundancy.

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?

With no output schema, the description carries the return-value burden and does so for the main fields (face_found, point_id, embedding, reason=no_face) as well as the 422 quality-gate path. It omits other error shapes and any limits on collection size or per-user selfie counts, leaving modest gaps.

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 every parameter is already documented in the schema, including the idempotency_key retry semantics. The description adds essentially no new per-parameter meaning beyond restating the retry behavior, so the baseline of 3 applies.

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 ('Store a user's selfie in a collection') plus the downstream purpose (matching against collection photos), so an agent knows exactly what it achieves. It does not explicitly contrast itself with the similar sibling index_photo, so it stops short of full sibling differentiation.

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?

Gives clear usage context (enrolling a selfie so it can later be matched) and routes the agent forward to search_by_point_id using the returned point_id. It also covers the retry case via idempotency_key. It never states when NOT to use it or why one would pick index_photo instead.

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