Skip to main content
Glama

TranscriptLab

Transcribe uploaded audio

transcriptlab_start_audio_transcription

Finalize a signed upload and start speech-to-text on it. App-facing only: the uploader view calls it once the file is uploaded. Spends credits per audio minute.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "upload_id": "<upload_id>"
    },
    "name": "transcriptlab_start_audio_transcription"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNoSpeech model tier; defaults to auto (normal when available).
diarizeNoLabel speakers; defaults to false. Implies tier=premium.
upload_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only supply the safety profile (write, non-destructive, closed-world); the description adds the material facts an agent needs: the upload is consumed/finalized, credits are spent per audio minute, and this is a billing-relevant operation. It does not say whether credits are charged on failure or what happens if the upload is not yet complete or already finalized, which would be the remaining useful disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action, then the caller constraint, then the cost warning. Every sentence carries distinct information with no restatement of the title or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, an agent has no idea what comes back — presumably a job or transcript identifier, but that must be guessed, and there is a sibling (transcriptlab_get_job_status) whose existence suggests a handle is returned. The input and cost side is well covered, but the missing return/next-step information is a real gap for a job-starting tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% and the schema itself already documents tier (with enum and default) and diarize (including the 'implies tier=premium' interaction), so those need no help. The only genuine contribution is the implicit link that upload_id refers to a previously signed upload; no format, source, or error behavior for that id is given, so this is baseline-appropriate rather than additive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific compound action: finalize a signed upload and start speech-to-text on it. This clearly distinguishes it from transcriptlab_transcribe_file (which takes a file) and transcriptlab_begin_audio_upload (which only starts the upload), so an agent can pick correctly without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"App-facing only: the uploader view calls it once the file is uploaded" gives a concrete precondition (upload must already be complete) and effectively warns that this is the UI-flow entry point rather than the general-purpose transcription path. It stops short of naming the alternative to use for agent-driven transcription (e.g. transcriptlab_transcribe_file or transcriptlab_transcribe_media_url), so routing still requires inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.