stemlab_generate_batch

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false, so the safety bar is lower. Beyond that, the description discloses that this is async ("Returns a retained background job"), names the base effect flag (write), and warns that inference/download effects are conditional on permissions resolved via danceflow_component. That is genuine behavioral context an agent could not derive from the annotations alone.

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?

Three short, front-loaded sentences with no filler; the scope statement precedes the workflow routing. The telegraphic phrasing ("Base effect flags: write.") is dense to the point of ambiguity, but nothing is redundant.

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?

An output schema exists, so return-value detail is not required, and the async-job behavior plus the follow-up polling target are covered. For an 18-parameter job-creation tool, however, the description leaves major questions unanswered: what "bounded" constrains, what is being compared, what form source/output take, and what the batch produces.

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?

The schema exposes a nested arguments object with roughly eighteen properties (bpm, modes, low_pass/high_pass, normalize, length_policy, max_candidates, moving_average_beats, harness, seed, etc.) and almost none carry schema descriptions. The description adds no meaning for any of these — no explanation of what a "mode" is, what the filter arrays accept, or what source/output strings should contain. It only touches the permissions concept, leaving the bulk of the contract undocumented.

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 concrete verb and resource: "Create a bounded comparison batch from source audio or retained stems," and adds a genuine scope boundary with "without new separation." The only weakness is that "comparison batch" is domain jargon an agent must infer, and it never contrasts itself with the many sibling stemlab_* tools that also operate on stems.

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?

It gives useful post-invocation routing ("poll danceflow_job_status") and points to danceflow_component for conditional effects, which is real usage guidance. However, it never states when to choose this tool over a non-batch or already-separated workflow, nor what prerequisites the source must satisfy. Usage is implied by the workflow chain rather than explicitly framed.

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