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

Adds substantial context beyond annotations: 15-60s (up to 2 min) runtime, timeout/retry semantics, and the fact that re-running on an already-split clip returns existing stems immediately. The annotations (readOnlyHint=false, destructiveHint=false) already cover the mutation/safety profile. There is mild tension between idempotentHint=false and the described return-existing-stems behavior, but it is not a hard contradiction.

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 the action and outputs, followed by timing/retry facts. No filler; every clause earns its place.

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 no-output-schema, single-param tool, the description covers what it produces (stem clips, links), how long it takes, and how to handle timeouts. 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 a single parameter and 100% schema description coverage, the schema already explains the encoded clip id and its provenance. The description adds no parameter syntax or format detail beyond what the schema provides, so the baseline 3 is appropriate.

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: 'Separate a clip into 4 stem clips: drums, bass, vocals and other', and even names the outputs (clip ids, m4a/wav links). No sibling does stem separation, so the agent can select this unambiguously from name plus description alone.

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 operational context: the edit runs on a clip from a finished job/list/split, plus retry guidance ('if it times out, ask again') and the already-split shortcut. It stops short of explicit when-not-to-use or alternative routing, but no sibling performs this operation, so there is little to route away from.

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