Skip to main content
Glama

Create a video

create_video

Start a motion video from a public product URL or a prompt. Returns at once with status "queued"; poll get_video until it is "ready", then give the user video_url (needs the API key) or call share_video for a public link; poster_url is its cover image. Counts as one video per 30 seconds.

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": "create_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoPublic page to read for the product, brand, colours and copy, e.g. https://your-product.com
modelNoWriting model id, or "auto" (default).
voiceNoAdd narration. Default false.
aspectNoFrame. Default 16:9; 9:16 for vertical social.
imagesNoUp to 10 screenshots or images (PNG, JPEG, WebP, GIF; 5 MB each). use "screen" (default) puts one on screen; "style" is a look to match, never shown.
promptNoOne or two sentences describing the video, used alone or with url.
purposeNoad (default), demo, or launch.
secondsNoLength in seconds. Default 10.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / images
      Added value: +{
      +  "description": "Up to 10 screenshots or images (PNG, JPEG, WebP, GIF; 5 MB each). use \"screen\" (default) puts one on screen; \"style\" is a look to match, never shown.",
      +  "items": {
      +    "properties": {
      +      "data": {
      +        "description": "Or the image as a data URL: data:image/png;base64,...",
      +        "type": "string"
      +      },
      +      "name": {
      +        "description": "What it shows, e.g. \"new billing page\".",
      +        "type": "string"
      +      },
      +      "url": {
      +        "description": "A public image URL.",
      +        "type": "string"
      +      },
      +      "use": {
      +        "enum": [
      +          "screen",
      +          "style"
      +        ],
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "maxItems": 10,
      +  "type": "array"
      +}
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does it well: it discloses asynchronous behavior (returns at once with status "queued"), the polling loop required, that video_url is gated behind the API key, that poster_url is the cover image, and the throughput constraint of one video per 30 seconds. These are exactly the operational facts an agent cannot get from the schema.

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?

The core action is front-loaded and every clause carries information — lifecycle, polling target, output fields, sharing path, rate limit. It is a single heavily semicolon-chained sentence, and the closing "Counts as one video per 30 seconds" is slightly cryptic without a rate-limit label, which costs a point on readability.

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 an 8-parameter creation tool with no annotations and no output schema, the description covers the async return, the polling step, both output artifacts (video_url, poster_url), the sharing alternative, and the rate limit. An agent has everything needed to call it and handle the result correctly.

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%, so every one of the 8 parameters is already documented, including enum meanings and defaults. The description only restates that a URL or prompt drives creation and adds nothing about defaults, limits, or interactions between url and prompt beyond what the schema says. Baseline 3 applies.

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?

"Start a motion video from a public product URL or a prompt" gives a specific verb (start) and resource (motion video) plus the two input modes. It is immediately distinguishable from get_video, share_video and revise_video, which are all named or implied elsewhere in the text.

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

Usage Guidelines4/5

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

The description explicitly routes the agent downstream: poll get_video until "ready", then surface video_url (needs API key) or call share_video for a public link. That is clear when-to-use-next guidance. It does not say when to prefer revise_video over re-creating, or when not to use this tool at all, so it stops short of the top score.

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