Submit a public video or audio URL (YouTube etc.) for verbatim transcription. Returns a job_id immediately. Transcription takes ~1-10 minutes: poll get_job with the job_id every 30-60 seconds until status is 'done', then call get_job with include_transcript=true. Not for private/internal URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already signal mutation, open world, and non-idempotence, and the description adds substantial behavioral context: immediate job_id return, 1–10 minute processing time, polling cadence, and the need for include_transcript when retrieving results. No contradiction with annotations.
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 three sentences, each adding critical information: action, return value, timing, polling procedure, and a constraint. It is front-loaded and free of 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?
The description covers input scope, immediate output, asynchronous timing, polling instructions, and final transcript retrieval, making it reasonably complete for a submit tool with no output schema. It omits error or rejection behavior, but the operational workflow is strong enough to guide an agent.
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?
While the schema has no description for the url parameter, the description compensates by specifying it must be a public video/audio URL (e.g., YouTube) and excludes private/internal URLs. It could be more detailed about supported platforms or formats, but for a single string parameter this is adequate.
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 uses the specific verb 'submit' with a clear resource ('public video or audio URL for verbatim transcription') and states the immediate return of a job_id. This fully distinguishes it from sibling tools like get_job, list_jobs, and delete_job.
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 explicitly says when to use the tool (public URLs), when not to use it ('Not for private/internal URLs'), and provides a concrete workflow: poll get_job every 30–60 seconds until status 'done', then call get_job with include_transcript=true. This is strong, actionable guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool performs a distinct lifecycle action: submit, get, list, and delete. There is no overlap in purpose, and the descriptions clearly differentiate when each should be used.
All tools follow a consistent verb_noun pattern: submit_transcription, get_job, list_jobs, delete_job. The naming is predictable and aligns with the domain.
Four tools are well-scoped for a simple transcription job management service. Each tool earns its place without unnecessary bloat or missing essentials.
The core job lifecycle is covered: create, list, retrieve, and delete. The only minor gap is the lack of a cancel operation for queued or running jobs, but the provided flow is complete for typical use.