Skip to main content
Glama

Generate a video

generate_video

Starts a video with a genframe model and charges the account's credits (refunded if it fails). Videos take about 1–6 minutes: the result gives a job_id; call get_job with wait_seconds to get the link when it is ready. Optional first/last frame pictures as public https URLs or links from this server.

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": {
      "prompt": "<prompt>"
    },
    "name": "generate_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
audioNoSound, for models that offer it (may change the price).
modelNoVideo model id from list_models. Default: an inexpensive model.
promptYesWhat happens in the video. Any language. 3–1500 characters.
durationNoSeconds, one of the model's options.duration (default 5 when offered).
resolutionNoOne of the model's options.resolution, e.g. 480p, 720p, 1080p (1080p and above need the Про plan).
aspect_ratioNoFor example 16:9, 9:16, 1:1. With a first frame the frame's proportions win.
last_frame_urlNoPicture to end on (only models whose inputs.last is true; needs first_frame_url).
first_frame_urlNoPicture to start the video from (image-to-video).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing credit charging with refund-on-failure, the 1–6 minute runtime, and the async job_id handoff to get_job. It also constrains frame inputs to public https URLs or links from this server, which the annotations do not cover.

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

Conciseness5/5

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

Three tightly packed sentences ordered by importance: what happens, cost, latency and how to retrieve the result, then input constraints. No redundant phrasing.

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 async, credit-consuming mutation with no output schema, the description covers cost, failure refund, expected latency, and the exact follow-up call needed to obtain the video link. Nothing essential to correct invocation is missing.

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 already 100%, so the baseline is 3; the description earns extra by adding real meaning about frame URL sourcing (public https or server-hosted links) and reiterating the async result contract that parameter docs do not convey.

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?

States a specific verb and resource: 'Starts a video with a genframe model.' The video resource itself separates it from generate_image without needing to name a sibling, though no sibling is explicitly referenced.

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?

Gives clear operational context: this tool only starts the job and the actual result comes from calling get_job with wait_seconds. It also scopes frame input ('needs first_frame_url' is in schema). It does not explicitly state when to prefer this over generate_image or generate_preset, but the follow-up path is unambiguous.

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