sampler_slice

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

Annotations declare non-read-only, non-destructive, idempotent, but the description adds the substantive consequence: the clip is switched into slice mode and each slice receives a note, which is a real state mutation not visible from annotations. It also discloses the hard 92-slice limit, that slices are returned, and that the operation is undoable.

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 dense sentences, each carrying distinct information: purpose and modes first, then the hard limit, then the side effect, then the return/undo note. No filler and no repetition of the schema.

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 6-parameter mutation tool with no output schema, the description covers what it does, the constraint on clip size, the resulting state change, downstream consumers (clips.write_slices), the return value, and reversibility. Nothing an agent needs in order to call it 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?

With 100% schema coverage the schema already defines every parameter, so the baseline is 3; the description earns extra credit by explicitly coupling each enum value of mode to the parameter that matters for it and noting beats are resolved at "the clip's tempo." It does not add format or boundary nuance beyond that.

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?

Opens with a specific verb+resource ("Cut an audio clip into slices") and immediately enumerates the three cutting strategies, so the agent knows exactly what the tool does and how it differs from neighbors like audio_split_stems or clips_transform. The mode-to-outcome mapping makes the tool's identity unambiguous.

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 concrete selection guidance for each mode (transients→sensitivity, equal→count, beats→division) and an explicit size exclusion: "slice a short loop, not a whole song" due to the 92-slice cap. It stops short of contrasting with sibling tools that also manipulate audio, but the in-tool guidance is clear.

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