Transcribe a video's speech

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

Annotations already declare readOnlyHint=true and openWorldHint=false; the description reinforces and explains that by noting the transcription is made locally, so no network call is implied. It does not cover cost, runtime for long videos, or how timestamps are formatted, so it falls short of a 5.

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 short sentences, front-loaded with what is produced and then the routing condition. Nothing redundant or padded.

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 two-parameter read-only tool with no output schema, it conveys the shape of the return value (timestamped text) and where the work happens. It could say slightly more about what a timestamped transcript entry looks like, but an agent has everything needed to call it correctly.

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% and the schema already explains absolute paths, supported containers, .watch bundle folders, tilde expansion, and the 2-letter language code with auto-detect default. The description's 'local video' phrasing is consistent but adds no syntax or format detail, so baseline 3 applies.

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 the specific output (a timestamped transcript of speech), the mechanism (Whisper, run locally), and the boundary (text only, no images). That boundary alone separates it from watch_video and frame without opening either 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 explicit trigger conditions: use it when watch_video reported a pending transcript, or when only the words matter. It names the sibling and the situation that routes the agent here versus to the visual tools.

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