propose_audio_transient_warp

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description is fully consistent with them — no contradiction. Beyond annotations, it adds substantial behavioral context: the operation is 'heuristic, source-only, no edit or audible validation,' meaning results are approximate and unverified; it 'reports signed offsets... for every candidate, including candidates skipped for marker actions,' disclosing the exact reporting behavior; and it instructs that actions should be 'individually dry-run... before applying,' flagging an important workflow caveat. This goes well beyond what the structured annotations convey.

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 sentences, every one earning its place: the first states the purpose, the second the return/reporting behavior, the third the limitations and usage caveat. The primary action is front-loaded, and there is no fluff, redundancy, or repetition of schema or annotation content.

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?

With no output schema, the description correctly takes on the burden of explaining return values: it reports signed offsets from the clip-relative beat grid for all candidates, including skipped ones. Annotations cover the safety profile and the schema covers parameters. The only notable gap is unit ambiguity in 'signed offsets' (beats vs seconds vs samples is not stated), and there is no explicit mention of how proposed marker actions map to the add/move sibling tools — minor for a proposal-only tool but worth clarifying.

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 100%, so the baseline of 3 applies — the schema already documents all six parameters well (e.g., gridBeats as 'Positive beat-grid spacing, e.g. 0.5 for eighth notes' and clipId's arrangement-clip support). The description's 'bounded source-audio onset candidates' loosely maps to startSeconds/durationSeconds but adds no concrete parameter-level meaning beyond the schema. It does not compensate for any gap because no gap exists.

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 states a specific verb and resource: 'Analyze bounded source-audio onset candidates and propose review-only marker actions toward a beat grid.' It clearly differentiates from applying-siblings like add_audio_warp_marker and quantize_audio_clip by emphasizing 'propose' and 'review-only' — this tool analyzes and suggests, it does not alter. The scope ('bounded'), method ('native Live source-to-beat conversion'), and goal ('beat grid') are all explicit.

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 clear context for when this tool fits: it is 'review-only' and 'dry-run actions against current state before applying,' implying it precedes actual marker application via siblings. It warns the agent that results are heuristic and unvalidated, so they must be reviewed before any apply-tool is used. However, it does not name the alternative apply-tools (add/move/remove_audio_warp_marker) explicitly, leaving that routing to inference.

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