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

Goes well beyond the annotations: it discloses that two new assets are created but not placed on the timeline, that both outputs share a single usage-credit charge, the ten-minute source-range cap, and the doubling pitfall if the original isn't muted. These are exactly the side-effect and cost details an agent needs before invoking a non-readOnly tool.

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 what the tool does, followed by cost/side-effect, range constraints, and the placement caveat. No filler and each sentence carries distinct information.

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?

With no output schema, the description usefully characterizes the return as two new project audio assets that are not auto-placed. The only material gap is the unexplained deecho flag, which an agent would have to guess at.

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 only 33% (media and project documented, from/to/deecho/workflow bare). The description compensates for from/to by specifying units (seconds) and a ten-minute cap, and the workflow enum is explained through the three stated operations, but the deecho boolean is never mentioned and range exclusivity is left 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?

The description names three concrete operations (clean voice, remove background music, split vocals/instruments) that map one-to-one onto the workflow enum, and the resource is unambiguous audio processing. This clearly separates it from generative siblings like generate_voice or generate_music, since it operates on source ranges of existing media.

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 three workflows give the agent clear in-context guidance on which mode to pick for a given goal, and the closing sentence explains the correct post-call workflow (place the returned media, mute the original). It stops short of naming when not to use it or pointing to an alternative sibling for adjacent needs.

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