find_repeats

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

With no annotations, the description carries the burden and does well: it discloses that nothing is changed, that each result proposes removing the FIRST take in favor of the later one, and that times are on the current timeline. It omits detection limits, cost/scope of the scan, and what happens for very short or long timelines, so it is strong but not exhaustive.

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?

Front-loaded with the purpose and examples, then behavior, then usage advice—every sentence adds information. The review caveat is slightly parenthetical but still earns its place by preventing blind cut_ranges calls.

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?

No output schema or annotations exist, so the description is the only specification; it covers result semantics (first-take removal proposals, current-timeline times) but leaves window_seconds undefined and does not describe the shape of each returned result beyond one proposed action.

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 single parameter window_seconds has 0% schema description coverage and the description never mentions it, so an agent cannot know it controls how far apart the repeated takes may be. This is the tool's only tunable and it is completely undocumented in both places.

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 (find) and resource (stutters, retakes, filler sounds) with concrete inline examples ("to new to new tech", um/uh), which is far more precise than a name restatement. It is clearly distinguishable from siblings like find_silences or transcribe because the artifact types it targets are named.

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 real downstream guidance: results are proposals 'ready for cut_ranges', and it instructs the agent to review and keep the first take when it is clearly better. It does not explicitly contrast with find_silences or say what context (whole timeline vs selection) it should be run in, so usage is clear but not fully framed.

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