Create a face

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the write/safety profile is covered. The description usefully clarifies that the bounding box content is treated as a face, but it says nothing about auth requirements, whether an existing personId must reference a real person, or whether duplicate faces are rejected.

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?

Short and front-loaded: verb+resource first, qualifying detail second, endpoint metadata last. The leading 'Create a face' line duplicates the title and the second sentence opens with the same phrase, which is minor redundancy rather than bloat.

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?

For a mutation tool with 8 required parameters and no output schema, the description covers intent and the bounding-box concept but omits key context an agent needs: required permissions, constraints on personId/assetId, and what the call returns. Annotations carry part of the load, so it is adequate but clearly incomplete.

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 the baseline is 3, but the schema 'descriptions' are placeholders like 'x (request body)' that convey almost nothing. The description adds only a partial hint that x/y/width/height form a bounding box; it does not explain personId, assetId, or how imageWidth/imageHeight relate to the box coordinates.

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 + resource ('Create a face') and adds a meaningful qualifier: the face must not already have been discovered by facial recognition, which separates it from auto-detected faces. It does not name or contrast with any sibling tool (e.g., immich_create_person, immich_get_faces, immich_reassign_faces), so it falls short of the 5 bar.

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 only implied by the clause 'that has not been discovered by facial recognition' – an agent can infer this is for manually registering undetected faces, but there is no explicit when-to-use/when-not guidance, no mention of the alternative immich_create_person, and no prerequisites such as the asset or person needing to exist.

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