stemlab_phrase_loops

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

Annotations already declare non-read-only, destructive, non-idempotent, closed-world. The description adds real value beyond them by disclosing that the call returns a retained background job requiring polling, and that effect flags are 'write' with conditional inference/download. It does not explain why a ranking operation is destructive or what state it changes, leaving the strongest annotation unelaborated.

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?

Four short statements, front-loaded with purpose then job behavior then effect flags and the escape hatch to danceflow_component. No filler, though the semicolon-chained clauses read as compressed internal shorthand rather than agent-friendly prose.

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 and the async-job contract is disclosed via the named poll tool, so the description needn't explain return values. However, for a write/destructive tool with 50% parameter coverage and no when-to-use statement, key invocation details (what evidence format, how thresholds affect results) are 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?

Schema description coverage is only 50% and the description adds nothing about the arguments object — none of results, feedback, top, min_lines, min_seconds/max_seconds, export_audio or max_bar_phase_error is explained. 'From saved evidence' loosely hints at the results payload but doesn't compensate for the coverage gap, especially for tuning thresholds.

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 ('Rank line-complete phrase auditions from saved evidence') and adds a scope limit ('no seamless-loop approval is inferred') that distinguishes it from a loop-approval tool. The phrasing is dense with domain jargon (line-complete, phrase auditions, seamless-loop), but an agent can still tell what the tool does and what it does not do.

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 follow-up guidance ('poll danceflow_job_status') and points to danceflow_component for conditional effects, which implies its place in a workflow. It never states when to choose this over sibling stemlab tools or what evidence input is required, so usage is only implied.

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