Skip to main content
Glama

studio_link

Read-onlyIdempotent

Returns a link to the Cuecaps studio set up exactly as the user described: the style, font, colors, how the spoken word stands out, the animation, size, format and language, plus a summary of what it sets up and the steps to give the user: they open it, add their video, click Find words and export an MP4 with captions burned in, a transparent overlay or an SRT or VTT file. With fast, the link also turns on Fast edit as soon as the words are found, cutting dead space, filler words and retakes, punching in on the jump cuts and levelling the volume. The video stays on their device. Works on every plan, Free included; exporting with Fast edit comes with Creator and Pro.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "studio_link"
  }
}

Input Schema

NameRequiredDescriptionDefault
animNoHow each caption comes in: pop, punch (slams down from large), bounce, rise, slide, fade, focus (from a blur), typewriter (letter by letter) or none.
caseNoLetter case: upper for capitals, lower, or as-spoken.
fastNoFast edit tools to turn on once the words are found: deadspace cuts the pauses, fillers cuts um, uh and stutters, retakes keeps the last take of a restarted sentence, zoom punches in on the jump cuts, norm levels the volume to -14 LUFS. all turns on every one.
fontNoCaption font, in place of the style's own.
langNoThe spoken language. Give it for any video that isn't in English; auto lets cloud transcription detect it.
markNoHow the spoken word stands out: color it, a box behind it, grow it, dim the words not yet spoken, reveal words as they are spoken, or none.
sizeNoCaption size as a percent of the style's own: 125 for bigger, 80 for smaller.
colorNoText color: a hex value such as #FFFFFF, or white, black, yellow, gold, orange, red, pink, purple, blue, cyan, green, lime.
linesNoLines per caption.
styleNoCaption style. list_styles shows how each one looks.
voiceNotrue removes background noise, music and room sound from the voice once the words are found (Clean up voice, a Fast edit tool; runs on the graphics card in Chrome or Edge on a computer).
wordsNoWords per caption; 1 shows one word at a time.
aspectNoFrame shape: 9:16 for TikTok, Shorts and Reels, 1:1 or 4:5 for feed posts, 16:9 for YouTube.
emphasisNoColor of the key words the studio picks for emphasis, as a hex value or a color name.
positionNoWhere the captions sit in the frame.
highlightNoColor of the word being spoken, as a hex value or a color name. A style that doesn't color the spoken word starts to.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / properties / anim
      Added value: +{
      +  "description": "How each caption comes in: pop, punch (slams down from large), bounce, rise, slide, fade, focus (from a blur), typewriter (letter by letter) or none.",
      +  "enum": [
      +    "pop",
      +    "punch",
      +    "bounce",
      +    "rise",
      +    "slide",
      +    "fade",
      +    "focus",
      +    "typewriter",
      +    "none"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / case
      Added value: +{
      +  "description": "Letter case: upper for capitals, lower, or as-spoken.",
      +  "enum": [
      +    "upper",
      +    "lower",
      +    "as-spoken"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / color
      Added value: +{
      +  "description": "Text color: a hex value such as #FFFFFF, or white, black, yellow, gold, orange, red, pink, purple, blue, cyan, green, lime.",
      +  "type": "string"
      +}
    • addedInput schema / properties / emphasis
      Added value: +{
      +  "description": "Color of the key words the studio picks for emphasis, as a hex value or a color name.",
      +  "type": "string"
      +}
    • addedInput schema / properties / font
      Added value: +{
      +  "description": "Caption font, in place of the style's own.",
      +  "enum": [
      +    "TikTok Sans",
      +    "Montserrat",
      +    "Poppins",
      +    "Inter",
      +    "Nunito",
      +    "Rubik",
      +    "Outfit",
      +    "Sora",
      +    "League Spartan",
      +    "Bricolage Grotesque",
      +    "Unbounded",
      +    "Kanit",
      +    "Space Grotesk",
      +    "Archivo Black",
      +    "Anton",
      +    "Bebas Neue",
      +    "Oswald",
      +    "Luckiest Guy",
      +    "Bangers",
      +    "Lilita One",
      +    "Titan One",
      +    "Permanent Marker",
      +    "Instrument Serif",
      +    "DM Serif Display"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / highlight
      Added value: +{
      +  "description": "Color of the word being spoken, as a hex value or a color name. A style that doesn't color the spoken word starts to.",
      +  "type": "string"
      +}
    • addedInput schema / properties / mark
      Added value: +{
      +  "description": "How the spoken word stands out: color it, a box behind it, grow it, dim the words not yet spoken, reveal words as they are spoken, or none.",
      +  "enum": [
      +    "color",
      +    "box",
      +    "grow",
      +    "dim",
      +    "reveal",
      +    "none"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / size
      Added value: +{
      +  "description": "Caption size as a percent of the style's own: 125 for bigger, 80 for smaller.",
      +  "maximum": 200,
      +  "minimum": 50,
      +  "type": "integer"
      +}
    • addedInput schema / properties / voice
      Added value: +{
      +  "description": "true removes background noise, music and room sound from the voice once the words are found (Clean up voice, a Fast edit tool; runs on the graphics card in Chrome or Edge on a computer).",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / fast
      Added value: +{
      +  "description": "Fast edit tools to turn on once the words are found: deadspace cuts the pauses, fillers cuts um, uh and stutters, retakes keeps the last take of a restarted sentence, zoom punches in on the jump cuts, norm levels the volume to -14 LUFS. all turns on every one.",
      +  "items": {
      +    "enum": [
      +      "all",
      +      "deadspace",
      +      "fillers",
      +      "retakes",
      +      "zoom",
      +      "norm"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  3. Changed1 schema field changed
    • changedInput schema / properties / lang / enum
      Previous value: -[
      -  "auto",
      -  "en",
      -  "es",
      -  "pt",
      -  "fr",
      -  "de",
      -  "it",
      -  "nl",
      -  "da",
      -  "sv",
      -  "no",
      -  "fi",
      -  "pl",
      -  "tr",
      -  "ru",
      -  "uk",
      -  "ar",
      -  "hi",
      -  "id",
      -  "vi",
      -  "ja",
      -  "ko",
      -  "zh"
      -]New value: +[
      +  "auto",
      +  "en",
      +  "es",
      +  "pt",
      +  "fr",
      +  "de",
      +  "it",
      +  "nl",
      +  "da",
      +  "sv",
      +  "no",
      +  "fi",
      +  "pl",
      +  "tr",
      +  "ru",
      +  "uk",
      +  "ar",
      +  "hi",
      +  "id",
      +  "vi",
      +  "ja",
      +  "ko",
      +  "zh",
      +  "bn",
      +  "cs",
      +  "tl",
      +  "el",
      +  "he",
      +  "hu",
      +  "ms",
      +  "fa",
      +  "ro",
      +  "ta",
      +  "th",
      +  "ur"
      +]
  4. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare read-only, closed-world, idempotent, non-destructive behavior, yet the description adds genuinely new context: the video stays on the user's device, it works on all plans including Free, Fast edit export requires Creator or Pro, and voice cleanup runs on the GPU in Chrome or Edge on desktop. It does not cover link lifetime or whether repeated calls produce a new studio each time, which is a real gap for an idempotent-flagged generator.

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 purpose is front-loaded, but the first sentence runs over a hundred words with the export flow and plan details strung together by commas, making it hard to parse. Most content earns its place, but the packing into a single run-on sentence costs readability.

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 16 optional parameters, no output schema, and no required arguments, the description correctly takes on the burden of explaining the return value (a link plus a setup summary and steps to relay to the user) and the plan/privacy constraints. It stops short of stating what the link points to over time or whether each call creates a fresh studio, which matters for a builder tool with no output schema.

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% with rich per-parameter descriptions and enums for eight parameters, so the schema carries the semantics. The description only re-groups the same fields at a high level (style, font, colors, how the spoken word stands out, animation, size, format, language) and adds no format, default, or precedence guidance beyond that.

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 states a specific verb and resource: it returns a link to a Cuecaps studio configured to the user's described style, font, colors, emphasis, animation, size, format and language, plus a summary and next steps. That is concrete and distinguishable from list_styles, though the sibling routing is left to the schema's mention of list_styles rather than the description itself.

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?

Usage is implied rather than stated: the agent can infer this is the tool for producing a ready-to-use studio link, and the description supplies the user-facing flow (open it, add video, Find words, export). There is no explicit when-not-to-use or named alternative, so an agent must infer the boundary with list_styles on its own.

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.