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

Annotations are empty, so the description carries the full burden, and it excels: it discloses asynchronous processing ('returns a tool_job hashid and status: queued'), polling expectations, output formats (json/srt/vtt URLs), free/rate-limited nature, file caps, and the non-substantive 'nudge' field. This is rich context that goes beyond what any structured field could provide.

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 structured into four clear paragraphs: core purpose, upload setup, async processing, and limits/notes. Every sentence adds necessary context—no filler—and the main action is front-loaded.

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 tool involving upload state, async job polling, and rate limits, the description covers everything an agent needs: how to prepare input, how to avoid the wrong pipeline, how to retrieve results, and what to do on rate limits. No output schema exists, but the description explains the return shape sufficiently.

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 descriptions already explain each parameter ('e.g. "en", omit to auto-detect', 'Defaults to true', 'from create_upload ... or list_videos'). The description essentially restates this same information, adding pipeline context but little new parameter-level meaning. Baseline 3 is appropriate given high schema coverage.

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: 'Transcribe an already-uploaded video ... into time-coded text.' It clearly differentiates from the paid clip pipeline by explicitly warning 'Do NOT call complete_upload for transcription,' and from other siblings like get_transcript by framing this as the job-starting tool.

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 when-to-use and when-not-to-use guidance: it says to use create_upload for local files, not to use complete_upload because that starts the paid pipeline, and to poll get_tool_job_status for results. It also covers optional parameters and rate-limit conditions, so an agent knows exactly how to select and invoke this tool.

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