transcribe_and_add_subtitles

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

With no annotations, the description carries the full burden. It discloses local execution and auto-chunking, but does not detail side effects (e.g., timeline modifications, resource consumption) or prerequisites. Adequate but not comprehensive.

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 concise: a two-sentence introductory paragraph followed by a clean parameter list with one line each. Every sentence adds value without redundancy.

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 (transcription + subtitles) and the presence of an output schema, the description covers the main behavioral aspects and parameter usage. However, it could further clarify the integration with the timeline (e.g., whether subtitles are added as markers or clips) and describe the return value, though that may be covered by the output schema.

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 description adds meaning beyond the schema by listing each parameter with a brief explanation: file_path (absolute path), model (Whisper sizes), language (code or auto-detect), initial_prompt (optional vocab guidance). This compensates for the 0% schema description coverage, though could include file format constraints.

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 the tool transcribes audio with mlx-whisper and adds subtitle markers to the timeline. It specifies local execution and auto-chunking for any file length, distinguishing it from siblings like transcribe_audio which may not add subtitles.

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 mentions that long files are auto-chunked, implying it works for any length, but does not provide explicit guidance on when to use this tool versus alternatives like transcribe_audio or create_subtitles_from_audio. No when-not-to-use or comparative context.

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