Edit a mix

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

Annotations only say idempotentHint=false and destructiveHint=false; the description adds crucial behavior: dry runs show a diff without sending anything, and commits create a new revision rather than overwriting the original. This explains the non-idempotent, non-destructive nature far better than the hints alone and sets correct expectations for repeated calls.

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 sentences, front-loaded with the main action, then the two behavior-critical facts: dry run default and new-revision commit. No filler and no duplication 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 complex 6-parameter tool with many op variants, the combination of description and fully-described schema is largely complete: the agent knows what action is taken, the safety model, and where parameters are described. The only real gap is that there is no output schema and the return/diff payload is only alluded to as 'shows the diff,' leaving result shape unspecified.

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 100%, and the schema itself documents every parameter, including dryRun, isPublic, revisionId, description, allowUnverifiedEffects, and the ops enum with rich descriptions like the volume automation envelope. The description does not attempt to repeat this, so it correctly leaves the schema to carry the load; no additional meaning is added beyond the dryRun/new-revision behavior.

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 opens with a clear verb and resource: 'Applies mix operations to a revision,' which tells the agent this is the mutation counterpart to read-only siblings like bandlab_get_mix and bandlab_list_revisions. It does not explicitly name an alternative or contrast itself, so it misses the top tier, but the purpose is 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?

The description gives operational context—dry run by default, dryRun=false to commit—and the revision-creation behavior, which tells the agent the safe way to preview changes. It never states when to choose this over bandlab_raw_request or bandlab_get_mix, nor gives exclusions, so usage guidance is implied rather than explicit.

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