Skip to main content
Glama

Create a VibeCreator video

create_video
Read-onlyIdempotent

Checks a script written in the VibeCreator format and returns a link that opens it as an animated video in the user's browser, where they can preview it, edit every part and export the MP4. The video is built from the script by code; no image or video model is used and nothing is stored.

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": {
      "script": "<script>"
    },
    "name": "create_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
brandNoOptional handle shown in the video, for example "@mychannel".
styleNoVisual style id from list_styles (for example "palito" or "jornal"). Leave it out and the site picks one by topic.
formatNoFrame shape. Default 9x16 (vertical).
scriptYesThe script object described by get_script_format: { title, lang, cast, scenes: [{ place, time, mood, beats: [{ say, ... }] }], post }.
characterNoHow the cast is drawn: "cara" = white round head with an expressive face and stick limbs (the classic viral stickman look), "palito" = black head with big eyes, "desenho" = cartoon person, "ilustrado" = hand-drawn people, "anime" = 3D anime cast, "nenhum" = no characters. Leave it out to keep the choice the user already made on the site.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint, idempotent, non-destructive, closed-world), the description explains that the video is generated deterministically by code with no image/video model, that nothing is stored, and that the browser link supports preview, per-part editing, and MP4 export. This resolves the key ambiguity of a tool named 'create_video' that is in fact read-only and stateless.

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?

Two sentences, front-loaded with the core validation-plus-link behavior, followed by the non-obvious implementation caveat. Dense but not padded; the only mild weakness is that the first sentence packs three distinct ideas (check, return link, edit/export) into one long clause.

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 five parameters at full schema coverage, rich annotations, and no output schema, the description covers the essentials an agent needs — notably that the return value is a URL rather than a rendered asset. Gaps remain around validity failure modes and link lifetime/persistence, which matter for a tool whose output is a URL.

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%, with enums, defaults, and cross-references to list_styles and get_script_format already documented per parameter, so the baseline is 3. The description reinforces that the script is the single driving input and that all rendering derives from it, but it adds no format or syntax details for brand, style, format, or character beyond what the schema states.

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 gives a specific pair of actions — validate a VibeCreator-format script and return a browser link where the animation can be previewed, edited, and exported as MP4. It also corrects the likely misreading of the name 'create_video' by clarifying that no video file is produced server-side. It does not explicitly contrast with get_script_format or list_styles, which are only referenced from 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 Guidelines3/5

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

The prerequisite that the script must be 'written in the VibeCreator format' is stated, and the schema points to get_script_format and list_styles for producing valid inputs. However, there is no explicit when-to-use vs. when-not guidance, no mention of what happens on an invalid script, and no statement about whether the tool can be called repeatedly on the same script.

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.

Resources