Transcribe speech into a word-timestamped caption element

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

Discloses behavior beyond annotations: runs Whisper in the server process without API key or third-party upload, requires ffmpeg, and by default adds to the current project unless add:false. It also explains the layer default behavior. These are valuable context traits not present in the sparse annotations. Minor gaps remain, such as expected runtime or return format, but output schema covers return shape.

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?

Five sentences, each with a distinct purpose: purpose, rationale, input modes, prerequisite, and default behavior. No redundant or filler content, and the most important information is front-loaded. The structure is crisp and scannable.

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 7-parameter tool with an output schema and minimal annotations, the description covers purpose, why this tool is needed, execution details, prerequisites, parameter flexibility, and side effects. It is complete enough for an agent to reliably select and invoke it without additional lookups.

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%, giving a baseline of 3. The description adds meaning beyond the schema by explaining the practical use cases for url vs path (chat-mode vs local), the layer stacking fallback, and model selection guidance ('tiny.en' for speed, 'small' for accuracy). This context is genuinely helpful for selecting parameters.

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 action and resource: 'Transcribe an audio or video file into a word-timestamped caption element.' It uses a specific verb and resource, and distinguishes this tool from generic siblings (like add_element) by emphasizing that only this tool provides real per-word timings via speech-to-text.

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?

Provides explicit context for when to use URL vs local path ('use this in chat-mode, where there is no local file'), notes the ffmpeg prerequisite, and explains the add:false option to avoid modifying the project. However, it does not explicitly name alternatives like add_element for non-transcribed captions, so it misses a clear exclusion statement.

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