Skip to main content
Glama

generate_video

Creates MP4 videos from text prompts or animates a local image guided by a prompt, with configurable resolution, frame count, and seed.

Instructions

Generate a video from a text prompt, or animate input_image (a local image path) guided by the prompt.

Default model: Wan 2.2 TI2V 5B at 1280x704, 49 frames (about 2 s) at 24 fps, 20 steps, MP4 (H.264). frames must be 4n+1 (rounded down otherwise), up to 121 (5 s). Expect several minutes per clip on this GPU; longer clips and higher resolutions take proportionally longer. Returns the MP4 path, seed, settings, timings and the effective backend idle timeout.

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
fpsNo
seedNo
modelNo
stepsNo
widthNo
framesNo
heightNo
promptYes
output_dirNo
input_imageNo
negative_promptNo
idle_timeout_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does well: it names the default model and exact defaults (1280x704, 49 frames, 24 fps, 20 steps, MP4/H.264), the frame divisibility rule, the cost profile ('several minutes per clip... proportionally longer'), and the returned fields including the effective backend idle timeout. It stops short of saying whether a backend must first be started (a start_backend sibling exists) or what happens to existing files in output_dir.

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?

Dense and front-loaded: the mode split comes first, then defaults, then constraints, then cost, then return value. Nearly every sentence adds information, though the block is a single long paragraph and the return-value sentence could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter generative tool with no annotations and no output schema, describing the return payload is a genuine plus. But gaps remain around negative_prompt, seed behavior, backend lifecycle prerequisites, and output_dir overwrite behavior, which an agent would need to call this reliably.

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 0% across 12 parameters, so the description must compensate and it partly does: prompt, input_image, frames (4n+1, max 121), and defaults for model/width/height/fps/steps are all covered. However, negative_prompt is never mentioned, and the semantics of seed (random when null?) and idle_timeout_seconds (what value is 'effective' and why it is returned) remain unexplained, leaving several parameters ambiguous.

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 specific verb and resource ('Generate a video') and immediately splits the two operating modes: text-to-video from 'prompt', or image animation when 'input_image' (a local path) is supplied. This is clearly distinguishable from the media-generation siblings such as generate_image or generate_turnaround without inspecting any 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 two modes imply when each parameterization applies, but there is no explicit guidance on when to choose this over generate_image or other siblings, no prerequisites, and no statement of when not to use it. Usage is inferable rather than stated.

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