Skip to main content
Glama

Transcribe and index media

ingest
Idempotent

Transcribe a YouTube video, podcast episode (Apple Podcasts, Spotify-with-RSS, RSS, Buzzsprout, Libsyn, etc.) and add it to the user's searchable library. Already-transcribed media returns instantly at no cost. Otherwise it runs as a job: waits up to wait_seconds, then returns status "queued"/"running" — poll get_job. quality "premium" re-transcribes with high-accuracy ASR when the account's plan includes it (best for multi-speaker interviews). Charged by route: captions 0.5 credits, ASR 20/hr, AI video 36/hr, podcasts 10/hr; worst case is reserved up front and the difference refunded.

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": {
      "url": "<url>"
    },
    "name": "ingest"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesYouTube video URL or podcast episode URL (or a yt: item id)
qualityNostandard
wait_secondsNo

Output Schema

NameRequiredDescriptionDefault
urlNo
nextYes
errorNo
job_idNo
resultNo
statusYes
item_idYes
qualityNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / result / properties / truncated_at_seconds
      Added value: +{
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations (idempotent, non-destructive, open-world) by disclosing credit costs per route, that the worst-case cost is reserved up front and refunded, that premium re-transcribes via high-accuracy ASR only when the plan includes it, and the exact status values returned. These are precisely the billing and async behaviors an agent cannot infer from structured fields.

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 action and resource, then layered with cost and async behavior in a compact sequence. The semicolon-chained cost sentence is dense but every clause carries decision-relevant information, so there is no padding to cut.

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

Completeness5/5

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

For a three-parameter, non-destructive write tool with an output schema available, the description supplies everything needed to call it correctly: blocking behavior, job lifecycle, cost model, and the plan dependency for premium quality. Return formatting details are rightly omitted because the output schema covers them.

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

Parameters4/5

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

Schema coverage is only 33%, and the description compensates for most of it: 'premium' is explained as a re-transcribe with high-accuracy ASR suited to multi-speaker interviews, and wait_seconds is clarified as how long the call blocks before returning a job status. The url parameter's accepted forms come from the schema rather than the description, so a small gap remains.

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 verb (transcribe) plus the resource scope (YouTube videos and podcast episodes across named providers) and the outcome (added to the user's searchable library). The job/poll framing also separates it from the read-only siblings get_transcript and get_job without needing their schemas opened.

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 clear conditional routing: already-transcribed media returns instantly at no cost, otherwise it becomes a job and the agent must poll get_job after wait_seconds. It does not explicitly state when to prefer get_transcript or discover instead, so alternatives are implied rather than spelled out.

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.

Resources