export_captions

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

Beyond the `readOnlyHint` annotation, the description adds meaningful behavioral context: it 'Records nothing' and explicitly says the caller must write `body` to a file themselves. It also discloses that captions are returned in time order and that cue text is 'as it stands,' which prevents assumptions about retiming or normalization.

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 compact and front-loaded: it states the output type, the source and ordering, the return payload, the caller's required follow-up, and the side-effect guarantee. Each sentence adds distinct necessary information with no filler.

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?

Because there is no output schema, the description correctly explains the return contract as `{ format, cues, body }` and tells the agent how to use `body`. It covers lane selection, ordering, and read-only guarantees; the only minor omission is the internal shape of the `cues` array, which is not essential for writing `body` to a file.

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 parameters are already well documented. The description reinforces the meaning of `format`, `track_id`, and composition selection, and adds the time-order behavior, but it does not provide substantial parameter-specific detail beyond what the schema already supplies.

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 clearly states that the tool returns the captions of a composition as a subtitle document, with `format` restricted to `srt` or `vtt`. It also defines the source scope (all lanes or one `track_id`) and ordering, which clearly distinguishes it from caption-mutating siblings like `apply_subtitles` or `restyle_captions`.

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 provides clear context for when to use the tool: when you need a subtitle document from existing caption lanes and want the cue text as-is. It does not explicitly name alternatives or state when not to use it, but the read-only export framing and 'Records nothing' signal the correct use case without needing further inference.

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