Plan Chapter Markers

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

Annotations already carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value beyond those hints by disclosing local-only computation ('TextTiling-lite' runs locally) and explicitly stating 'never changes Premiere', which makes the no-side-effect contract concrete for an agent. No contradiction with annotations.

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 dense sentences with no filler: purpose and algorithm first, then return shape, then side-effect safety. Every clause earns its place, and the most decision-relevant fact ('never changes Premiere') is positioned at the end as a crisp guarantee.

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?

Given the tool's complexity (nested word_timeline object, 7 params), the schema carries the full parameter burden at 100% coverage, annotations carry the safety profile, and an output schema exists so the return structure need not be spelled out. The description covers what remains: the algorithm, the three output components, and the local-only guarantee. A minor gap is the absence of an explicit prerequisite pointer to get_clip_transcript_uxp, though the schema's transcript_revision pattern communicates it.

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 input schema already documents all seven parameters, including defaults and constraints on frame_rate, block_words, title_words, max_chapters, and min_chapter_seconds. The description's algorithm language ('topic-shift detection', 'titling from distinctive tokens') loosely maps to stop_words, block_words, and title_words, but adds no parameter-specific meaning beyond what the schema already provides. 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 names a specific verb+resource ('Plan YouTube-style chapters from a word-timed transcript') and adds a distinctive algorithm ('TextTiling-lite topic-shift detection', 'titling from distinctive tokens'). This clearly separates it from planning siblings like plan_silence_review_markers, plan_beat_montage, and plan_filler_word_removal without needing to open any schema.

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 makes the usage context clear: the caller supplies a word-timed transcript and receives a plan, not a Premiere mutation. Mentioning 'add_marker-ready Chapter markers' implies the follow-on application step, and 'Local-only plan; never changes Premiere' clarifies this is a planning-stage tool. However, it does not explicitly name alternatives or when-not-to-use conditions.

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