Skip to main content
Glama

TranscriptLab

Read a speech-to-text transcript

transcriptlab_get_speech_transcript
Read-only

Read the speech-to-text transcript started by transcriptlab_transcribe_file (pass upload_id) or transcriptlab_transcribe_media_url (pass media_id). Pass exactly one id. While transcription runs it returns a pending result: wait a few seconds, back off, and stop after about ten tries; if it is still pending, tell the user the job is queued instead of looping. Reading does not start new work or add charges.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "transcriptlab_get_speech_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoDefaults to json.
media_idNoFrom transcriptlab_transcribe_media_url.
upload_idNoFrom transcriptlab_transcribe_file.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely new behavior: pending results during active transcription, recommended backoff and a ~10-attempt cap, plus the reassurance that reading starts no new work and adds no charges. The main omission is what a completed result actually contains, though the format parameter hints at output shapes.

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

Conciseness4/5

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

Front-loaded with the core action, then the id-selection rule, then the polling policy. Three tight sentences with no filler; only slight redundancy in restating the two source tools already described in the schema.

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

Completeness4/5

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

With no output schema, the description does need to cover return behavior, and it covers the pending case well with concrete retry limits. The success-case payload is left implicit and the format enum values are only named in the schema, but for a single-job read tool the coverage is nearly sufficient.

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 description coverage is 100%, so the schema already documents format, media_id and upload_id including their source tools, making 3 the baseline. The description does add one constraint the schema omits — that exactly one of the two ids must be supplied despite zero required parameters — which is useful but marginal beyond the structured fields.

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

Purpose4/5

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

States a specific verb and resource ("read the speech-to-text transcript") and ties it to the two producer tools by naming which id each supplies. It does not differentiate itself from the several other read-ish siblings such as transcriptlab_get_transcript or transcriptlab_retrieve_transcript, so the purpose is clear but not fully disambiguated from the catalog.

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?

Gives explicit calling conditions: pass exactly one of upload_id or media_id, poll while pending, back off, stop after about ten tries, and report queued status to the user rather than looping. That is strong when-to-use and when-to-stop guidance. It stops short of naming an alternative read tool for the non-transcription case.

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.