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

Annotations only say readOnlyHint=false; the description adds that the footage is genuinely shortened, that losses are irreversible ('Not undoable'), and that a transcript must exist first. That is meaningful disclosure beyond the annotations, though it does not say what happens to clips/transcript alignment afterward or whether the change lands on the current timeline version.

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?

Three short sentences with zero waste: effect first, disambiguation second, prerequisite and irreversibility last. The emphasis capitals on 'OUT OF THE FOOTAGE' are doing real work against the most likely misreading.

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, non-undoable mutation with no output schema, the description covers effect, irreversibility, and the transcript prerequisite well enough to call it safely. It could still say more about scope (whole project vs selected range) and what the caller gets back to confirm the edit.

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% and both keep_ms and min_silence_ms carry their own defaults and tuning caveats, so the schema does the heavy lifting. The description only gestures at keep_ms via 'keeping a little breathing room at each one' without adding units or thresholds beyond 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 concrete verb and effect on a concrete resource: silent pauses are cut out of the footage, which literally shortens the video. The line 'not a transcript cleanup' separates it from transcript-span operations, but it never mentions close siblings like studio.remove_silence or studio.cut_transcript_span, so an agent still has to guess which of the near-identical tools to pick.

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?

'Needs a transcript first (transcribe)' gives a real prerequisite and 'Not undoable' flags risk, which is useful selection context. But it never states when to prefer this over studio.remove_silence, studio.remove_fillers, or studio.cut_transcript_span, so alternative routing 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.