repair_episode_dialogue

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses that video is not regenerated, audio is re-synced from cloned voice, there is a lip-sync cost, the operation runs async serially, progress is checked via dialogue-repair-status, billing is per TTS chunk, and insufficient balance aborts without charge.

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?

Although long, the description is dense and front-loaded: purpose first, then scope, alternatives, costs, caveats, and required follow-up. Each sentence earns its place, and the emphasized warnings (mouth sync, billing, compose requirement) are essential for correct use.

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 description covers all essential operational context for a complex async tool: defect scope, exceptions, cost model, alternatives, failure behavior, progress checking, and mandatory post-step. Even without an output schema, it explains how to track the operation and what to do after completion.

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?

Two of three parameters (force and only_flagged) are already well-documented in the schema, including defaults and effects. The description adds no meaningful parameter semantics beyond what the schema provides, and episode_id is left implicit. Since schema coverage is 67%, the description does not need to compensate heavily, but it also does not add value over the schema.

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 opens with a specific verb+resource: batch-repairing episode dialogue where lines are truncated or off-script. It further distinguishes itself from siblings by explicitly contrasting with replace_shot_dialogue and regenerate_shot_video, so an agent can select it correctly without opening schemas.

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 explicit when-to-use guidance: default only repairs defects flagged by scan_dialogue_coverage (truncated/off_script/extra_speech), explicitly says minor_gap should not be touched, and directs users to regenerate_shot_video instead when the episode is mostly close-up dialogue. It also instructs to run compose_episode afterward, leaving no ambiguity about follow-up actions.

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