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

Annotations only declare it is a non-destructive, idempotent write; the description adds real behavior the agent cannot get elsewhere: the split point, downstream ripple on the clip's own tracks, and the silence under a trailing hold. It is still silent on permissions, undo, and what's returned beyond 'the edit result', which is punted to server instructions.

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?

Two front-loaded sentences with nearly zero waste; the primary effect comes first and the edge case second. Minor nits: the doubled 'at at_frame' phrasing and the deferral '(see the server instructions)' push context off-tool.

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 an output schema present, return values needn't be described, and the enumerated other_tracks/preview parameters are fully documented in the schema. The description covers the operation, its ripple effects, and the trailing-frame special case — everything needed to call it correctly.

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 67%, and the description supplies the key semantics the schema lacks: that at_frame is the held frame and duration_frames is how long, plus the edge-case meaning when at_frame is the clip's last frame. other_tracks, preview and timeline_id are left entirely to the (well-written) schema fields.

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 ('hold the frame at at_frame for duration_frames') and spells out the composite effect: the clip splits, a freeze frame is inserted, and later clips ripple. That composite signature separates it from clip.split and create.still without the agent having to infer anything.

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 a concrete usage context and an important special case ('freezing a clip's last frame holds it after the clip, with silence under the hold'), which tells the agent when the result differs from the common case. It does not name sibling alternatives such as clip.split for pure cuts, so it stops short of explicit when-not guidance.

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