Skip to main content
Glama

Generate a video with Grok Imagine (experimental)

grok_generate_video

Creates a short Grok Imagine video from a text prompt, optionally animating a local image, and returns MP4 file paths.

Instructions

EXPERIMENTAL: make a Grok Imagine video (about 6 s) from a prompt, optionally animating a local image (image_path: jpg/png/webp). Videos cost much more quota than images and are capped by max_videos_per_day (see grok_usage). Relies on Grok's current web UI, which changes often. Returns {"files": [mp4 path]}.

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": "grok_generate_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
aspectNo
promptYes
out_dirNo
timeout_sNo
image_pathNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

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 (readOnly=false, openWorld=true, non-idempotent): it warns the tool depends on a frequently-changing web UI, flags the quota cost relative to images, notes the daily cap, and discloses the return shape. That is exactly the operational risk context the annotations cannot convey.

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?

Five dense sentences, front-loaded with the EXPERIMENTAL warning and cost caveat; no filler, and the return shape is compressed to a single fragment.

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?

For a 6-param mutation tool with no output schema and no annotations on cost, the description covers output shape, quota risk, and fragility. It falls short only on the undocumented optional parameters (notably aspect and timeout behavior), which an agent may need before invoking.

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 0%, so the description carries the burden; it explains prompt and image_path (with accepted formats jpg/png/webp) and hints at output via 'mp4 path'. However, name, aspect, out_dir, and timeout_s get no meaning at all, and 'aspect' is genuinely consequential for video generation, so compensation is only partial.

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+resource ('make a Grok Imagine video'), adds duration (~6 s) and an optional image-to-video mode, which distinguishes it from the sibling grok_generate_image. An agent can tell exactly what this produces without opening 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 Guidelines4/5

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

Sets clear context: experimental, costly in quota, capped by max_videos_per_day, and routes the agent to grok_usage for limits. It does not explicitly say 'use grok_generate_image for stills instead', so the alternative-routing is implied rather than stated.

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