youtube-kit

by eukosh

Overview Schema Source Related Servers Discussions Admin

Python

Local

Get Transcript

get_transcript

Read-onlyIdempotent

What is said in one of your videos, from its captions, including the ones YouTube generates.

Instructions

What is said in one of your videos, from its captions, including the ones YouTube generates.

YouTube lets only a video's owner download its captions. Of several tracks in a language, one YouTube is serving is preferred over one it failed to process, then a published one you wrote over YouTube's.

Quota: 252 units.

Input Schema

Name	Required	Description	Default
`video`	Yes	Video ID or URL.
`format`	No	text: paragraphs of about 30 seconds, each starting with its [m:ss] time. srt or vtt: the caption file itself.	text
`language`	No	Caption language, e.g. en or en-US. Omit for the language spoken in the video.
`my_channel`	No	Which of your logged-in channels to work on: UC… ID, @handle or exact title. Omit for the default channel.
`translate_to`	No	Machine-translate the captions into this language, e.g. de.

Output Schema

Name	Required	Description
`kind`	Yes
`text`	Yes
`format`	Yes
`language`	Yes
`video_id`	Yes
`caption_id`	Yes
`translated_to`	No	Language YouTube machine-translated the track into.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.7.1Oct 22, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description adds ownership/authentication requirements, track-selection behavior, and a concrete quota cost of 252 units. These details materially help an agent predict whether the call will work and what it will cost.

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?

The description is short and front-loads the core purpose before adding ownership constraints, track preference, and quota. Every sentence contributes useful context, with no filler.

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 read-only transcript retrieval tool with full schema coverage and an output schema, the description covers the critical behavioral context: ownership restriction, caption track choice, and quota. Nothing essential for correct invocation is missing.

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%, and the schema already documents video, format, language, my_channel, and translate_to. The description adds no parameter-level semantics beyond that structured documentation, so the baseline of 3 is appropriate.

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?

The description clearly states that it returns what is said in one of the user's videos from captions, including YouTube-generated captions. The resource and content are specific, but it does not explicitly distinguish itself from sibling tools such as list_captions.

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

Usage Guidelines3/5

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

It gives an important usage constraint: only a video's owner can download its captions, and it explains track preference. However, it does not explicitly say when to use this instead of list_captions, upload_caption, or update_caption.

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