Skip to main content
Glama

Make show notes from a transcript

make_show_notes

Use this after transcribe_media, or when the user has a transcript, for "write show notes for this episode", "add YouTube chapters to my video", "pull the best quotes". Pass exactly one of transcript_id (with library_id when transcribe_media gave one), transcript (the text, or an SRT or VTT file) or url (the same link). Returns a summary, chapters with times and YouTube chapter lines, up to 3 quotes with times, keywords, Markdown show notes and post_topic for draft_posts. Fixed rules pick sentences as spoken; no model, no cost.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "https://www.youtube.com/watch?v=jNQXAC9IVRw"
    },
    "name": "make_show_notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoThe same link given to transcribe_media: a public YouTube, TikTok, Instagram or other social video, or a direct audio or video file link. It is transcribed again under Transcript Kit's daily minutes; transcript_id costs nothing.
titleNoEpisode or video title for the notes (default: the transcript's title).
library_idNoThe library_id that same transcribe_media answer gave, such as lib_9b6a98861ea4f54bff8f5cf1. Pass it with transcript_id when the answer had one.
transcriptNoThe transcript itself: plain text, or the text of an SRT or WebVTT file (its times become chapter times), up to 60000 characters.
transcript_idNoThe transcript_id a transcribe_media answer gave, such as tr_a6f8c87a9b2eb748. Give exactly one of transcript_id, transcript or url.
confirm_rightsNoWith url only, as for transcribe_media: true only after the user says they own the recording or may use it. A public social video needs none.

Output Schema

NameRequiredDescriptionDefault
noteYes
as_ofYes
notesYes
titleYes
sourceYes
statusYesok: the notes are ready. A refused call returns an error text such as "transcript_not_found: ..." that says what to do next.
summaryYes3 to 5 sentences from the transcript that carry its most repeated words, in spoken order.
chaptersYes
keywordsYesThe words said most often, for tags.
languageYesSpoken language as an ISO 639-1 code; null for pasted text.
key_quotesYesUp to 3 sentences of 8 to 35 words, as spoken, for a quote card or a post.
post_topicYesThe title and summary in one paragraph, as the topic of a post about the episode.
word_countYes
duration_secondsYesLength of the recording; null when the transcript had no times.
untrusted_sourceYes
youtube_chaptersYesThe chapters as lines to paste into a YouTube description (0:00 first, 3 or more, each 10 s or longer); null when that is not possible.
description_markdownYesSummary, chapters, quotes and keywords as Markdown to paste under the episode or video. Markdown signs in the spoken text are escaped, but a bare www. or http(s):// address or an email address in it is not, so it becomes a link where GitHub Flavored Markdown is rendered: check links before publishing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond annotations by disclosing cost and resource behavior: scores are produced by fixed rules with "no model, no cost," url is re-transcribed and consumes daily minutes while transcript_id is free. It also names the rights/consent condition for url input. It does not, however, say what happens on failure or whether the output is persisted anywhere, which is the remaining gap for a non-readOnly tool.

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?

Ordered well: when to use, then inputs, then outputs, then behavioral note. Every sentence carries information, though the middle input sentence packs three alternatives into one dense clause and the return-value sentence is somewhat redundant with the output schema.

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 six-parameter, open-world tool with an output schema, the description covers triggers, all three input modes, the rights gate, and the cost model. An agent can select and invoke it correctly without opening the schema, and the output shape is already carried by the output schema.

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 100%, so baseline is 3, but the description adds a constraint the schema cannot express: the zero-required, six-optional schema silently permits all or none of the three input variants, and the description closes that hole. It also clarifies that transcript may be an SRT or VTT file and that its times become chapter times, adding semantics beyond the field text.

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?

Uses a specific verb+resource (make show notes) and immediately names the concrete artifacts produced: summary, chapters, quotes, keywords, Markdown notes. The example user phrasings ("write show notes for this episode", "add YouTube chapters", "pull the best quotes") pin down the scope precisely and separate it from drafting siblings like draft_posts and draft_video_script.

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?

Explicit trigger conditions are given: "Use this after transcribe_media, or when the user has a transcript," and the upstream tool is named. It also states the mutually exclusive input selection rule (exactly one of transcript_id, transcript, or url) and notes the library_id pairing constraint, which is the main invocation pitfall.

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.