Skip to main content
Glama

generate_video

Generates videos from text prompts via OpenRouter, polls asynchronously until complete, and downloads the video file to disk.

Instructions

Generate video from text prompt via OpenRouter (Veo, etc). Async — polls until complete, downloads video file.

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
seedNoSeed for deterministic output
modelNoModel ID (default: google/veo-3.1)
promptYesText description of the video
durationNoDuration in seconds
output_dirNoSave directory (default: ./generated)
resolutionNo480p, 720p, 1080p, 2K, 4K
aspect_ratioNo16:9, 9:16, 1:1, 4:3, 3:4
generate_audioNoGenerate audio track (default: false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and does disclose two critical traits: the call is asynchronous and polls until complete (so the agent knows it may block for a long time) and it downloads a video file to disk as a side effect. It omits cost, failure/timeout behavior, and whether the remote job can be cancelled, keeping it from a 5.

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?

Two compact clauses with zero filler; the core action is front-loaded and the async/download behavior follows immediately. Nothing could be removed without losing information.

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?

An eight-parameter generation tool with no output schema needs the description to say what comes back; 'downloads video file' implies a local file and the output_dir parameter suggests a path, but the actual return value is not stated. The async and file-writing behavior is covered, leaving this adequate but with a real gap.

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 all eight parameters (model, seed, duration, resolution, aspect ratio, generate_audio, output_dir) are already documented in the schema. The description adds no meaning beyond 'text prompt' and does not explain how model choice interacts with duration or resolution options, so baseline 3 applies.

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 ('Generate video from text prompt') and names the backend ('via OpenRouter (Veo, etc)'), which cleanly separates it from generate_image and text_to_speech. It does not explicitly name a sibling or state differentiators beyond the output medium, so it falls short of a 5.

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?

Usage is only implied: the agent can infer this is the tool for text-to-video work. There is no explicit when-to-use guidance, no mention of list_video_models for discovering valid model IDs, and no stated limits on prompt content or model selection.

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