place_voiceover

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

With no annotations, the description carries the full burden and does well: it discloses that the duck is applied as volume keyframes only where the voice speaks, that gaps longer than 0.35 s release the music, that fades are short, and that the keyframes remain editable in Effect Controls. It omits what happens if no free track exists and whether a track gets created, and says nothing about failure modes for an unimported file.

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?

The primary action and its ducking behavior are front-loaded in the first sentence, with the prerequisite routing last. It is dense but each clause carries information; the nested parenthetical about silences is the only spot that slows parsing.

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 no annotations and no output schema, the description covers the important behavior: placement target, track selection, ducking via keyframes, and editability afterward. Remaining gaps are the 'file' input form (path vs project item) and the no-free-track case, neither of which is recoverable from the schema.

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 the baseline is 3; the description still adds meaning by explaining the placement modes ('at the playhead or at seconds') and how duckTracks resolves when omitted ('Music = audio-only clips on other tracks, or the tracks in duckTracks'). It does not clarify whether 'file' is a filesystem path or a project item, or how silenceDb interacts with the 0.35 s rule.

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 composite resource: place a voiceover file on the timeline at the playhead or a given second, on the first free audio track, and duck the music under it. That composite scope clearly separates it from add_to_timeline, setup_ducking, and add_audio_keyframes, which each do one piece.

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?

The description makes the trigger condition clear (you already have a voiceover file and want placement plus ducking in one step) and routes the agent elsewhere for the missing prerequisite: 'To record a voice first, use a text-to-speech tool or skill.' It gives no explicit when-not guidance or comparison against the ducking/keyframe siblings.

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