Search a collection by face

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

Goes well beyond the annotations by disclosing the cost (93 credits), the return shape ({photo_id, score} best first, plus photo_ids), and the named failure reasons (no_face, low_quality_selfie). The annotations already flag openWorldHint and idempotentHint, and the description's cost disclosure usefully explains why readOnlyHint is false; only rate limits and the semantics of 'score' are left implicit.

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?

Three dense sentences: what it does, what it returns, what failures mean, and what it costs — front-loaded with the core purpose and free of filler. Every clause carries distinct information an agent needs before calling.

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 contract itself and does so: match list shape, ordering, parallel photo_ids, and reason codes for empty results. Combined with the 100%-covered schema and the cost disclosure, nothing material is missing for correct invocation.

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 description coverage is 100%, so every parameter is already documented in the schema, including the embedding origin and the calibrated default for threshold. The description adds no syntax, format, or precedence guidance beyond what the schema already provides, 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 with scope: find photos in a collection matching the person in a query image or a 512-number embedding. The 'in a collection' scoping separates it from a standalone face comparison, but it never names the neighboring tools (compare_faces, detect_faces, search_by_point_id) it should be distinguished from.

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 is implied rather than stated: 'typically a selfie' hints at the common input, and the embedding path is described, but there is no explicit when-to-use vs. when-to-use-a-sibling guidance and no note on choosing among the five query modalities (file_path, image_url, gcs_key, image_base64, embedding).

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