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

Annotations only say non-read-only, non-destructive, non-idempotent; the description goes well beyond by disclosing that results are saved as an undoable version (undo_edit), cost no Horizon Units, and are asynchronous — returning a job_id that must be polled via job_status then preview_frame. It also notes captions follow the footage, which is a real behavioral consequence of retiming.

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-loaded with the trigger before the parameter reference, then alternatives, then side effects and return path — a logical progression with little waste. The quoted user utterances are slightly verbose but earn their place by disambiguating near-miss intents.

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 mutating, asynchronous, six-parameter tool this covers the gaps that matter: parameter ranges and defaults, mutual intent of speed/freeze/remove, cost, undoability, and the follow-up toolchain. An output schema exists, so the brief return note is sufficient rather than redundant.

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 0%, so the description must carry all meaning — and it does: clip_id provenance (list_clips), time units (seconds of the clip as it plays, 0:12 = 12), speed range 0.25–4 with a worked example (0.5 = half speed), end_seconds default of 0 meaning the clip's end, freeze_seconds range 0.1–10 holding the frame at start_seconds, and remove=true cutting the range. All six parameters are covered with ranges and semantics absent from the schema.

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 — retiming part of a clip — and immediately scopes it with four concrete user phrasings (slow down, speed up, freeze, cut out). It is clearly distinguishable from style_clip (whole-clip speed) and edit_clip (silences, trimming), which are named.

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?

Opens with an explicit when-to-use trigger tied to natural user requests, then adds a 'Not for:' block that routes three adjacent intents to their correct siblings (style_clip for whole-clip speed, edit_clip for silences/filler and for trimming ends). Nothing is left to inference.

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