stemlab_generate_cues

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

Goes materially beyond the annotations by disclosing that the operation is asynchronous and returns a retained job, that the base effect is a write, and that inference/download effects are conditional and must be checked via danceflow_component. This complements readOnlyHint=false and destructiveHint=false with what actually gets mutated and what permissions gate it. It stops short of stating whether a generated job can be cancelled cleanly or how long retention lasts.

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: purpose first, then the async follow-up action, then the permission model. Every sentence carries information an agent needs before calling.

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 write-classified, async, nested-schema tool the description covers the job lifecycle and permission model well, and an output schema exists so return values need no explanation. The major remaining hole is that an agent still cannot tell what to put in the nested arguments object beyond guesswork.

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 only 50%, and the description explains none of the nested arguments — 'results', 'output', 'artist', 'title', 'downbeats', 'precision', 'beat_model', 'tolerance_ms', and 'fail_on_review' are left with no semantic explanation in either place. Only 'retained song evidence' loosely hints at what 'results' should contain, which is not enough for a ten-property nested 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 and product ('Generate beat-linked cues') plus the input source ('retained song evidence'), which tells an agent what it produces. It does not, however, distinguish itself from close siblings like stemlab_snap_cues, stemlab_match_clip, or stemlab_generate_batch, so the agent cannot infer which cue-generator to pick from this 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 useful downstream guidance — the call returns a background job and the agent must poll danceflow_job_status — which is real usage context. It offers no guidance on when to choose this tool over the many sibling generators, and no stated preconditions (e.g., that retained evidence must already exist).

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