Skip to main content
Glama

video_transcript

Extract a YouTube video's transcript, using manual subtitles first then auto-captions, with language selection, timestamped chunks, and start/end ranges to read only part of long videos.

Instructions

Get video transcript (manual subs first, then auto-captions). lang='auto' (default) uses the video's spoken language; or force e.g. 'en', 'tr'. Lines merge into ~chunk_seconds blocks (0 = raw) to save tokens. Use start/end ('1:30') to read one part of a long video. No captions? use transcribe_video.

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": "video_transcript"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
urlYes
langNoauto
startNo
max_charsNo
chunk_secondsNo
with_timestampsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it discloses source preference order (manual subs before auto-captions), the token-saving merge behavior, and the timestamp format. It leaves out auth/permission needs and any rate-limit or cost considerations, and relies on the output schema for return shape.

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?

Four short sentences, each covering a distinct decision point, with the primary behavior front-loaded. No filler or restatement of the tool name; the parenthetical asides are functional rather than decorative.

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?

The tool has a moderate 7-parameter surface and an output schema, so return values need not be explained, and the description covers the main usage decisions well. The remaining gap is the unaddressed max_chars and with_timestamps parameters, which an agent would have to infer from their names alone.

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 0%, so the description must compensate for all 7 parameters. It explains lang, chunk_seconds (including the 0 = raw sentinel), and start/end with a concrete '1:30' format example, but says nothing about max_chars or with_timestamps, leaving two meaningful parameters undocumented in both places.

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 and resource ('Get video transcript') and immediately scopes the behavior: manual subs first, then auto-captions. It explicitly names the sibling transcribe_video as the fallback, so an agent can distinguish the two without opening either schema.

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

Usage Guidelines5/5

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

Gives concrete when-to-use guidance for each option: lang='auto' vs forcing a code, chunk_seconds for token savings with 0 = raw, and start/end for reading part of a long video. It also names the alternative tool and the exact condition that selects it ('No captions? use transcribe_video').

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