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

Goes well beyond the annotations by disclosing that the call returns immediately with a Job ID, media is produced in the background, output is a new full-length sound asset in sync from the first second, and the exact cost model (0.63 credits/second, ~38 credits for a 1-minute clip). Annotations only cover the read/write and idempotency profile; the description adds the operationally critical async, cost, and output-shape details.

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?

Purpose is front-loaded in the first sentence, and the remaining sentences cover placement, async behavior, and cost — all functional. It is dense and slightly long, but every sentence carries real information with little waste.

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 an async, cost-bearing generation tool with no output schema, the description is complete: it explains the immediate Job ID return, the background processing model, how to retrieve results (wait_for_jobs → Asset ID for patch_film), and how to integrate the result on the timeline. Nothing an agent needs to invoke and follow up correctly 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 coverage is 100%, so both parameters (assetId, projectId) are already fully documented in the schema, including the 30-minute limit and null-project behavior. The description adds no new parameter-level syntax or format detail, so the baseline of 3 applies.

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+resource ('Clean the speech of a video or a sound: keep the voices and remove the rest') with concrete examples of what gets removed (baby crying, wind, traffic, music, crowd, echo). It clearly distinguishes itself from siblings like split_sound, remove_background, and cutout_person by specifying voice isolation.

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 rich usage context: how to place the output (same at/offset/duration as the source clip, set that clip's volume to 0) and the async workflow (start jobs, keep working, call wait_for_jobs for Asset IDs). It does not explicitly name alternatives or when NOT to use it, so it stops short of a 5.

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