Separate stems

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

With no annotations, the description carries the full behavioral burden and delivers: runtime characteristics, CPU-only execution, progress reporting at 5% steps gated on a progressToken, a one-time model download prerequisite, and the exact failure codes (model_missing, demucs_unavailable) with their causes.

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?

Two dense sentences, front-loaded with what the operation produces, then prerequisites and failure modes. Efficient and information-rich, though the second sentence packs several distinct facts that could be easier to scan as a list.

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?

Covers the operation, its outputs as named tracks, performance cost, progress signaling, and error conditions, which is enough to invoke it correctly despite the absence of an output schema. It stops short of describing the exact response payload or what happens to pre-existing tracks on the target track.

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 all five parameters are already documented (defaults for clip, track, threads, mute_source). The description adds only the alignment guarantee with the source clip and does not clarify parameter interactions or defaults beyond 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 (splits) and resource (a clip) plus the exact outputs produced (Drums/Bass/Other/Vocals tracks) and the separator used (Demucs htdemucs). This is clearly distinct from the generic 'split' sibling, which gives no hint of stem separation.

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 clear context for using it: it is slow (minutes per song), CPU-only, and requires model weights downloaded via Settings > Separation. It does not name an alternative tool or state when NOT to use it, so it falls short of the explicit when/when-not/alternatives bar.

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