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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description earns credit by explaining exactly what survives — the earliest face's id and name, so existing bindings keep working — and what happens to the intervening time (left as a gap for the clip's gap policy). That is substantive consequence-level detail an agent cannot get from the annotations or schema.

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 short sentences, front-loaded with the action and scenario, then the refusal rule, then the survival/idempotency consequence. No filler and no repetition of schema text.

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 destructive 4-parameter mutation with full schema coverage and no output schema, the description covers usage, the hard refusal condition, identity survival, and downstream gap behavior. Nothing an agent needs to invoke it safely and correctly is missing.

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; the description adds a real constraint on faceIds beyond the schema's 'two or more within that run' — that no two may share a frame — which changes how an agent should build the call. It adds little about projectId/trackId/token, which the schema already documents.

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 concrete verb and resource — joins two or more faces from one run into a single person — and immediately grounds it in the real scenario (subject leaves frame and returns). That scenario framing distinguishes it from bind_face and track_faces without needing to name them.

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 an explicit when ('somebody who walked out of the shot and came back') and an explicit when-not/refusal condition ('REFUSED when any two of them appear on the same frame, since they cannot then be one person'). It stops short of naming the sibling (bind_face) an agent should use for the different-person case, so routing is inferred rather than stated.

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