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

Annotations only declare the safe-mutation profile (readOnly=false, destructive=false, openWorld=false); the description adds substantive behavior on top: generation is billed against the workspace's monthly voice/music minutes, length is clamped to 3-180 s, and the result is ducked under speech. Gaps remain on the approval flow (an `approvalId` parameter exists but the description never explains the needs_approval round-trip) and on what the call returns, which matters since there is no output schema.

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?

Four tight sentences, front-loaded with the action and destination, then prompt-crafting, then defaults/limits, then cost. The quoted example prompt and the billing note both earn their space; nothing is repeated from the schema verbatim.

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 7-parameter generative tool with no output schema, it covers the essentials an agent needs to call it correctly: prompt style, placement, duration bounds, and quota impact. The unexplained approval pathway and the absent return-value description are the remaining holes.

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?

Adds real meaning beyond the 71%-covered schema: it tells how to craft `prompt` (genre, mood, tempo, instruments, with a concrete example string), that `instrumental` defaults to true, how `duration` derives from the timeline with a 3-180 s bound, and that `start` governs placement. `volume`, `projectId`, and `approvalId` are left entirely to 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 (compose music via ElevenLabs) and names the exact destination (the Music track, from `start`, ducked under speech). That placement detail alone separates it from add_sfx, add_voiceover, and add_beat_markers without opening any 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?

The context of use is clear — an instrumental bed auto-ducked under speech, generated from a text description — which implicitly routes agents away from add_voiceover and add_sfx. It stops short of naming alternatives or stating exclusions (e.g., when to prefer an uploaded track via add_clip or import_media).

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