Detect Repeated Takes

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description complements these by adding a concrete promise: 'never changes Premiere' and 'Local-only,' plus the planning-only nature and the return of apply routes. It does not discuss failure modes or input validation, but for a read-only analysis tool the safety profile is well covered by annotations plus the added local-only promise.

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?

The description is two sentences that front-load the main function and conclude with safety and output summaries. It is compact but includes the key disambiguation: it detects and plans, it does not apply. It could be slightly tighter, but every clause carries information and the structure is scannable.

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?

The tool has an output schema, so return values are already specified elsewhere. The description covers input domain, algorithm family, output categories, and safety. It does not mention prerequisites like get_clip_transcript_uxp, although that is referenced inside the word_timeline schema. Given the schema richness and output schema presence, the description is sufficiently complete for correct invocation.

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 schema already documents all 8 parameters in detail, including defaults, bounds, and the word_timeline structure. The description adds the algorithmic framing ('token similarity within a time window') and the outputs, which helps an agent understand why parameters like similarity_threshold and max_gap_seconds matter. Since coverage is complete, baseline 3 is appropriate.

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 uses a specific verb ('detect', 'plan removal') and names the exact resource ('repeated sentence takes (retakes) in a word timeline') plus the method ('token similarity within a time window'). It also clarifies what it returns (take groups, removal/keep ranges, apply routes), which distinguishes it from generic detection tools. Among siblings like plan_filler_word_removal or detect_silence, this clearly stands out as take/retake detection and removal planning.

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 states the tool works on a 'word timeline' and is 'Local-only; never changes Premiere,' which gives clear context for when it is safe to use. It does not explicitly name alternative tools or exclusion conditions, but the word-timeline input requirement and read-only promise are enough to guide an agent away from direct Premiere mutation tools. A short 'use this before apply_edit_plan/preview_edit_plan' alternative note would have made it a 5.

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