stemlab_snap_cues

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the safety profile is largely covered elsewhere. The description does add real value beyond them by disclosing that this is an asynchronous retained job and that the base effect footprint is 'write' with possible conditional inference/download effects. It stops short of saying what gets overwritten in the cue/output files or what happens on failure given the fail_on_review flag.

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 sentences, front-loaded with the action, then the return contract, then the permission model. No filler. Slightly cryptic terms like 'retained detected beat evidence' cost a little clarity but nothing is wasted.

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 is present, so return values need not be described, and the annotations already carry the safety hints. The description covers the operation, the async follow-up tool, and the effect/permission model, which is enough for an agent to invoke it correctly. The remaining gap is per-parameter meaning, scored separately.

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 description coverage is 50% and the nested arguments object carries ten sub-properties (cues, output, results, precision, beat_model, tolerance_ms, force_snap, fail_on_review, downbeats, sample_rate) with no per-field explanation anywhere. The description only indirectly names two of them via prose ('supplied LRC', 'detected beat evidence') and never explains precision modes, tolerance semantics, or the review gate. It leaves most of the substantive parameters opaque.

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 concrete verb and resource pair: snapping a supplied LRC against 'retained detected beat evidence', and it names the async handoff (starts a background job). This lets an agent distinguish it from the pure analysis/inspection siblings, though it never explicitly contrasts with stemlab_generate_cues or stemlab_beat_offset, which sound adjacent.

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?

Guidance is implied through the workflow: it tells the agent to poll danceflow_job_status afterwards and to inspect danceflow_component for conditional effects beforehand. What is missing is the selection rule — when to snap existing cues versus generating cues or applying a beat offset with the sibling tools.

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