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

Beyond the annotations, it discloses that the edit is saved as an undoable version, that it costs no Horizon Units, that unsupported options are refused by name before any mutation occurs (fail-fast, no partial state), and that the call is asynchronous and returns a job_id. These are exactly the facts an agent needs to explain side effects, cost and follow-up to a user, which the readOnly/destructive/idempotent hints alone do not convey.

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 purpose and examples, then parameters, then exclusions, then lifecycle behaviour — a logical order with no filler sentences. It is dense and somewhat long, and the six-utterance example list could be trimmed slightly, but every block earns its place.

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 10-parameter mutation tool with an output schema and partial-safe annotations, the description covers cost, reversibility, failure mode, async job flow and sibling exclusions. Nothing needed to call it correctly or to narrate the result to a user 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 description coverage is 0%, so the description carries the full burden, and it does: it gives the source of clip_id, numeric ranges and meanings for original_volume, denoise, voice_boost and ducking_db, explains normalize and mute_original, enumerates accepted music_volume values (quiet/normal/loud or 0-400 percent) and voice_effect names plus 'off'. All ten parameters are given semantics that the bare schema titles lack.

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?

The opening states the purpose behaviourally ('when the user wants the sound of a clip changed') and then anchors it with six concrete request phrasings covering mute, volume, denoise, normalize, voice effect and music level. The 'Not for' clause explicitly separates it from edit_clip (song changes) and add_to_clip (momentary sound effects), so an agent can route without opening either sibling schema.

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?

Provides when-to-use in the form of real user utterances and when-not-to-use with named alternatives for both excluded cases. It also implies prerequisites via 'clip_id: from list_clips' and the downstream flow (poll job_status, then get_download_link), leaving little to inference.

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