create_caption_track

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

The description adds one behavioral detail beyond annotations: 'Creation is structural only; verify playback or exported frames before delivery.' This hints at limitations (no timecode adjustments or rendering) but doesn't specify side effects like whether an existing caption track is replaced, how the track is named/positioned, or whether the source file is embedded or linked. Annotations don't provide action information (readOnlyHint=false, no actionHint), so more transparency would be expected.

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?

Two concise sentences. The first sentence immediately states the purpose with specific verbs ('create', 'import') and the second adds a critical caveat. No fluff or repetition. Information density is high and well-ordered.

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?

There is no output schema, so the description must explain what the agent can expect after execution)Skip. It only says 'creation is structural only,' which is vague for an agent deciding whether to call this vs. other tools like export_sequence. Missing: whether the tool returns success/failure, whether the caption file must be pre-imported or can be a disk path, whether it works on the active sequence regardless of app state, and any preconditions (e.g., active sequence exists). These gaps could cause an agent to misuse the tool.

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 schema covers all parameters (item_id, start_seconds, caption_format) with description strings, giving 100% coverage. The description adds example file extensions for the caption file (.srt, .vtt) and clarifies that item_id is a name or name path. This is helpful, but the description doesn't explain what start_seconds offset means in context or whether caption_format is required or auto-detected. Overall, the schema's field descriptions do most of the work, and the description adds only modest extra context.

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 what the tool does: 'Create a caption/subtitle track in the active sequence from an imported caption file.' It names the specific resource (caption track in the active sequence), the input (imported caption file), and includes example file extensions. It's specific and actionable but doesn't explicitly distinguish from sibling tools since no other tool in the list handles caption creation.

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?

It indicates when to use the tool (when you have an imported caption file) and provides a delivery caveat ('verify playback or exported frames before delivery'). However, it doesn't explain when not to use it or reference any alternatives—though no other sibling tool appears to handle captions, so the omission is less critical. The guidance is adequate but not explicit about exclusions.

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