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

Annotations already flag destructive=true and idempotent=true, so the safety profile is partly covered; the description adds genuinely new behavior — motion is inherited relative to first-seen position while existing framing is preserved — and explains the unbinding mode. It does not say what the binding overwrites on the clip or how it interacts with existing keyframes.

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-loads the core action, then the mechanism, then the knobs, then the undo path — each sentence carries distinct information with no filler.

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 9-parameter mutation tool with a nested channels object, the description covers what the tool does, how motion is applied, and how to reverse it, while the fully populated schema handles parameter detail. The only real gap is not stating the dependency on a prior face-tracking run.

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 including gap, channels, smooth and maxGlideSeconds is already documented in the schema. The description reinforces channels/gap/trackId-null but adds no semantics beyond what those descriptions state. Baseline 3 is appropriate.

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?

Specific verb and resource: "Makes a clip FOLLOW a tracked face", plus concrete use cases (mask, label, blur). It is clearly distinct from the face-related siblings (track_faces, merge_faces, list_face_tracks) by what it produces, though it never names track_faces as the source of trackId, so the sibling relationship is implied 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?

Gives real usage context (attaching masks/labels/blurs to a head) and explains the two key optional knobs, channels and gap, in terms of when you'd choose them. It also documents the unbind path via trackId: null. It stops short of stating prerequisites, e.g. that a face track must exist first via track_faces.

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