create_caption_track

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

No annotations are provided, so the description carries full burden. It discloses that the track is created in the active sequence from a file, but does not explain side effects (e.g., overwriting existing tracks), error conditions (invalid file), or whether the file must be already imported. Minimal behavioral context.

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?

Single sentence of 13 words, front-loaded with the action verb. Every word is informative, no redundancy or fluff. Highly concise.

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?

For a mutation tool with 3 params and no output schema, the description provides the core action but lacks details on return value, success/failure behavior, and specific prerequisites. Schema covers param details, but behavioral gaps remain. Adequate but not thorough.

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%, with detailed param descriptions. The tool description adds only marginal value (e.g., file format examples .srt, .vtt already implied by schema). At high coverage, baseline 3 is appropriate; no significant additional meaning.

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 specifies the verb 'Create', resource 'caption/subtitle track', and source 'from an imported caption file' with examples .srt, .vtt. It clearly distinguishes from siblings like add_text_overlay (which does not use files) and add_marker.

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 implies use when an imported caption file is available and the sequence is active, but does not explicitly state when not to use this tool or mention alternatives among siblings. No usage exclusions are provided.

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