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

Annotations declare a non-read-only, non-destructive, non-idempotent operation, but the description adds value beyond them: 'It does not use credits' (cost), the limitation that a recorded song is not extracted from read_asset music (with notes in 'other' and singing in 'voices'), and that each requested part becomes a new aligned sound asset.

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 and allowed parts are front-loaded, and most sentences carry distinct information (outputs, alignment, track usage, song caveat, credit cost). Some sentences are convoluted ('the clip whose sound it stands in for'), which slightly hurts readability.

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 explains what is returned (new sound assets per named part) and how to use them, and covers cost and a key non-extraction limitation. It is nearly complete for a mutation tool, missing only details like idempotency or failure behavior.

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 100%, so the enum meanings for parts and the projectId/open-project behavior are already documented in the schema. The description largely restates that field information, so the baseline of 3 applies; the alignment detail ('in step from its first second') is about the output rather than a parameter.

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 ('Split the sound of a video or a sound into its parts') and enumerates the exact outputs (voices, drums, bass, other) with concrete examples for each. This clearly distinguishes it from siblings like isolate_voice, which extract only a voice.

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?

Gives strong procedural guidance: how to place the resulting parts on an audio track with matching at/offset/duration and zero the source clip's volume, and warns that omitted parts disappear. It does not, however, name when to prefer this over alternatives such as isolate_voice, so sibling routing is left implicit.

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