Transcribe audio (local Whisper)

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

Goes well beyond readOnlyHint/openWorldHint: audio never leaves the machine, the fallback chain is disclosed, real-time recording means the segment audibly plays, the first run downloads the model (latency/cost warning), and the tab path requires prior user permission. These are exactly the side effects and prerequisites an agent needs before calling.

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 core action and the locality guarantee are front-loaded, and every following clause carries operational information. It is a single dense paragraph with slightly long sentences but 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?

For a read-only tool with no output schema, the description covers the return shape (timestamped text in video time), the latency caveat (first-run model download), the permission requirement, and the fallback behavior. Nothing an agent needs to call it correctly is missing.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: it explains the source strategies behind the enum (decode vs. real-time stream vs. tab) and that model availability incurs a first-run download. It also clarifies that timestamps are in video time rather than wall-clock time.

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?

States a specific verb and resource (transcribe the speech of a video segment) plus the engine and locality (Whisper running locally). This distinguishes it from video_captions and video_watch, which an agent can now tell apart without opening the schema.

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?

Gives a clear decision rule for the audio source (decode when the media has a URL, otherwise real-time recording, then whole-tab as a last resort) and states the prerequisite for the tab fallback (user must have clicked the Kyte WebMCP icon). It does not explicitly name sibling alternatives such as video_captions for already-captioned media.

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