Skip to main content
Glama

Subtitle files from words with times

make_subtitles
Destructive

Generates SRT, VTT, and ASS subtitle files from timed speech-to-text words or existing caption files while leaving the video unchanged.

Instructions

Use it when the user wants an SRT, VTT or ASS subtitle file for a video. Writes subtitle files from words with times the user already has, and changes no video: captions.srt and captions.vtt, lines of up to 42 characters for any player or place that takes a captions file, captions.ass with the font, the colors and the place, laid out for the frame of the video given (else a phone's for tiktok, reels or shorts, a square for square alone, and 16:9 for the rest), and words.json, captions.json and CAPTIONS.md, which the result shows with how fast the captions read. The words are a speech-to-text JSON, an SRT or WebVTT file, or a demo's steps file, whose step notes become the captions; without video, a demo's captions end where its steps file says the video does. To burn the captions into the video, use caption_video instead. The captions playbook (makersmcp_playbook) has the whole job. (easycaptionkit 0.1.4, on this machine.)

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": {
      "words": "<words>"
    },
    "name": "make_subtitles"
  }
}

Input Schema

NameRequiredDescriptionDefault
boxNoA dark box behind the words in captions.ass instead of an outline.
forNoThe places the video goes to, whose free space captions.ass keeps to (default: the places of the video's shape, or of the frame laid out).
fontNoA font family for captions.ass, like Inter.
sizeNoThe letters' size in captions.ass, in percent of a phone's width or of the frame's short side, 2 to 20 (default 6.5, or 9.5 for the word style).
brandNoA brand kit, its folder or brand.json, for captions.ass's highlight color and font. make_brand_kit makes one.
fontsNoA font kit, its folder or fonts.css, for captions.ass's font. make_font_kit makes one.
linesNoLines a caption may take, 1 to 3 (default 2).
styleNoHow captions.ass shows them: karaoke lights the word being spoken (default karaoke), line shows whole captions, word one word at a time.
videoNoThe video the subtitles are for, read for its size and length only.
wordsYesThe words and their times: a speech-to-text JSON, an SRT or WebVTT file, a demo's steps.json, or the words.json of an earlier run with a misheard word fixed by hand.
out_dirNoFolder to save into, absolute or relative to /app. Default: <words-folder>/easycaptionkit-subtitles-<words-name>, where <words-name> is the name of words without its extension and <words-folder> is the folder words is in. A run replaces the files an earlier run of this kit left there, so give each version its own out_dir.
positionNoWhere in the free space captions.ass puts them (default bottom).
highlightNoThe spoken word's color in captions.ass, like #ffd23f.
max_charsNoCharacters a line of captions.srt and captions.vtt may take, 8 to 80 (default 42); captions.ass cuts its lines to what fits across its frame.
wait_secondsNoHow long to wait for the result, counted from the start of the call, before returning a job_id to wait on. Some clients end a call after 60 or 240 seconds; 45 is safe in all of them.

Output Schema

NameRequiredDescriptionDefault
kitYes
docsNoThe notes the text shows, and where each one is.
nextNoWhat to do next, as the Next line says.
toolYes
filesNo
folderNoWhere the kit saved its files.
job_idYes
passedNoFor checks: whether the check passed.
statusYes
continuedNoTrue when this call continued the job of an identical call whose answer did not reach the client, instead of starting another.
exit_codeNo
last_lineNoWhat the kit was doing last.
expires_atNoWhen the download links stop working.
next_actionNo
elapsed_secondsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A4.2/5.0
Behavior4/5

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

Goes well beyond the annotations by enumerating the exact files written (captions.srt, captions.vtt, captions.ass, words.json, captions.json, CAPTIONS.md) and by warning that a run replaces files a previous run left in that folder, which explains the destructiveHint=true annotation. It does not mention that the call is job-based and may return a job_id, even though the wait_seconds parameter implies asynchronous behavior.

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

Conciseness3/5

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

The trigger is front-loaded, but the remainder is a dense run-on sentence with stacked parentheticals about frame shapes and demo steps that is hard to parse on first read. The version/machine stamp adds traceability but is not needed for invocation.

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 15 parameters, an output schema, and full annotation coverage, the description covers input sources, produced files, the overwrite hazard, and the sibling for burning captions. The main omission is any mention of the asynchronous job/job_id flow that the wait_seconds parameter exposes.

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 coverage is 100% and the description largely restates what the schema already documents (42-character lines, karaoke default, frame-shaped .ass layout). It adds only modest framing by tying parameters to which output file they affect, so the baseline 3 for full schema coverage is appropriate.

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 concrete verb and artifact set ('Writes subtitle files from words with times'), names the exact formats (SRT, VTT, ASS), and explicitly separates itself from caption_video. An agent can pick this tool over its siblings without opening the 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?

Opens with an explicit trigger ('Use it when the user wants an SRT, VTT or ASS subtitle file for a video') and names the alternative plus the condition that selects it ('To burn the captions into the video, use caption_video instead'). It also points to the playbook for the full workflow, leaving little to inference.

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