dubbing_start_project

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

Annotations already declare a non-read-only, open-world, non-idempotent operation, and the description adds genuinely new behavior: audio is downloaded (video optionally for preview), transcripts come from captions or ASR, and speaker labels are derived from caption markers or pitch clustering. It does not warn that repeated calls create separate projects or that transcription can be slow/costly, which would be the remaining high-value disclosures for a write tool.

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 sentences, front-loaded with the action and accepted inputs, with no filler. The second sentence is a dense run-on stringing together download, transcription, merging and diarization, which is slightly harder to scan but every clause carries real information.

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 ingestion tool, the description covers the pipeline, the fallback logic, the diarization behavior and the return shape; the output schema makes the return-value restatement redundant but harmless. The only real omission is the semantics of project_name and source_language, which is minor against the overall completeness.

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 0%, so the description must carry the parameter burden, and it does explain most of them: source formats, num_speakers ('set if known'), download_video ('optionally the video for a preview'), prefer_captions, and captions_file via the SRT/VTT mention. Two parameters, project_name and source_language, are never addressed, leaving their meaning entirely to inference.

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 opens with a specific verb and resource ('Start a dubbing project') and immediately enumerates the three accepted source types (YouTube URL, local media file, SRT/VTT caption file), which distinguishes it from siblings that only inspect or mutate an existing project. It also states the output shape (project_id, duration, speakers, segment count), so an agent knows exactly what the tool produces.

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?

It gives conditional guidance inside the tool: captions are taken from YouTube when available, speech is transcribed otherwise, and 'set num_speakers if known' tells the agent when to supply that parameter. It does not name an alternative tool or a precondition (e.g., checking setup first) for the case where the agent is unsure whether projects can be started, so it falls short of explicit when/when-not routing.

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