transcribe_audioRe-transcribe recorded meeting audio with a selected provider or language after the call, enabling alternative transcription results.
Start a (re-)transcription of a bot's recorded audio with a chosen post-call provider. Useful to try a different provider or language after the meeting.
| Name | Required | Description | Default |
|---|---|---|---|
| bot_id | Yes | ||
| language | No | ||
| provider | No | deepgram | |
| callback_url | No | Webhook to notify when done |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It fails to disclose that this is likely an asynchronous operation, that re-transcription may overwrite existing transcripts, or any permission/rate-limit considerations. It only implies it runs post-call.
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 with zero filler. The action is front-loaded and the use case is a single clause.
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 with 4 parameters, no output schema, and no annotations, the description is too brief. An agent cannot know what the function returns, whether the transcription is asynchronous, or what prerequisites exist (e.g., bot must have recorded audio).
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 description coverage is only 25% (callback_url described). The description mentions 'provider' and 'language' in prose but does not explain bot_id, language format, or behavior of callback_url. It adds some context but not enough to compensate for the sparse schema.
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 states a specific verb ('Start'), resource ('a bot's recorded audio'), and adds the re-run capability, distinguishing it from read-only transcript retrieval siblings like get_transcript. It does not explicitly name siblings, but the action is unambiguous.
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 provides a concrete use case: 'to try a different provider or language after the meeting.' This covers when to use it, though it doesn't mention exclusions or alternative tools (e.g., get_transcript) explicitly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.