Skip to main content
Glama

Render a video

video_render

Renders a scene to video.webm (VP9 and Opus), video.wav (its sound) and video.vtt (when it has subtitles); with preview (the default) also video.contact.png, twelve moments on one sheet, and video.preview.gif, 480 pixels wide. A scene can hold: drawn pictures with groups (a character's parts move, turn and fade together) and mirror x, y or both on any layer or group, layer and track blends (multiply for a shadow, a vignette or a night grade; screen and add for a glow or a flare, on a layer or a track alike), closed paths filled nonzero (the default) or evenodd (a self-overlapping star leaves its centre bare);characters who talk (cast, timed lines with their own reading, ducked music, subtitles made from the lines, a mouth that moves on the words, or swaps between closed, open, wide and round drawings (with an idle breath and a listening beat, as a moving mouth has), and eyes that blink); shots with people on paths, action beats (guard, strike, hit, fall, get-up) and gestures on cue (a wave, a point, a nod), a directed character (a figure by seed, dressed by its look, standing in a named gait from the schema, speaking through its cast name, set among forms, props and a ground, filmed by a dolly or an orbit), animals and forms, and a camera that follows, orbits or cranes; music cues with a melody, a lead instrument, tempo changes and fades, that duck under lines and under any sound marked ducks_music; and sounds that move across the ears. Its files together are at most 50 MB, so a long, busy scene renders with preview false. At most 60 seconds, 1920 by 1080 either way up and 30 frames a second. The price is read off the engine's own cost report: units = design renders x megapixels / 45 + frames x megapixels / 200 + shot frames x megapixels / 1.6 + 3 a shot clip, rounded up; at most 600 a job, and video_cost says it first. It runs as a queued job: the answer is 202 with a job id at once, and GET /api/agents/jobs/ (or the MCP tool job) says when it is done and signs its files. A queued call is refused on the free plan with 402: its units buy only calls that answer at once, and queued jobs need the subscription. Each account may have 4 queued jobs waiting or running (1 running at a time), and may submit 20 videos and 10 minutes of video a day (UTC).

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": {
      "scene": "<scene>"
    },
    "name": "video_render"
  }
}

Input Schema

NameRequiredDescriptionDefault
sceneYesA scene document written inline: output (size, frame rate, length), tracks of clips, optional cast and lines, audio and subtitles. Start from video_examples and read video_schema for every key.
previewNoAlso write the contact sheet and a small preview GIF (the default); false for a long, busy scene whose files would pass the size cap.

Output Schema

NameRequiredDescriptionDefault
msNoMilliseconds the run took.
jobYesThe job id; the job tool reads it.
verbNoThe tool that made it.
filesNoFiles made, each with a name, type, size and a signed URL.
unitsNoUnits this call cost.
resultNoThe engine's own answer, a JSON document.
statusNoqueued when the job runs in the background.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": true,
      +  "properties": {
      +    "files": {
      +      "description": "Files made, each with a name, type, size and a signed URL.",
      +      "items": {
      +        "additionalProperties": {},
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "job": {
      +      "description": "The job id; the job tool reads it.",
      +      "type": "string"
      +    },
      +    "ms": {
      +      "description": "Milliseconds the run took.",
      +      "type": "number"
      +    },
      +    "result": {
      +      "description": "The engine's own answer, a JSON document."
      +    },
      +    "status": {
      +      "description": "queued when the job runs in the background.",
      +      "type": "string"
      +    },
      +    "units": {
      +      "description": "Units this call cost.",
      +      "type": "number"
      +    },
      +    "verb": {
      +      "description": "The tool that made it.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "job"
      +  ],
      +  "type": "object"
      +}
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries the burden and does so richly: the 50 MB file cap, 60-second/1920x1080/30fps limits, the exact cost formula and 600-unit ceiling, the asynchronous 202+job-id contract, the 402 refusal on the free plan, and concurrency/daily quotas. This is precisely the operational context an agent needs to call the tool without failure.

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

Conciseness2/5

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

The opening output list and the closing limits/cost/quota block are well placed, but the middle sentence is a sprawling catalogue of scene features (blends, fill rules, mouth drawings, dolly moves) that belongs in video_schema. Details like "a self-overlapping star leaves its centre bare" do not help an agent decide to call or invoke this tool and bury the critical limits and pricing.

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 a complex, async, expensive render tool with a nested scene document and an output schema, the description covers limits, billing, the queued-job contract, and plan/quota restrictions that the schema cannot express. Nothing essential to a correct invocation appears missing.

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 100% and both parameters are documented in the schema, including the preview default and its size-cap implication. The description repeats the preview guidance in its size-cap sentence but adds no new semantics for scene or preview, so the baseline of 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?

Starts with a specific verb plus resource ("Renders a scene to video.webm... video.wav... video.vtt") and enumerates the exact artifacts produced, including the preview outputs. An agent can immediately distinguish this from video_still or video_check without opening 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?

Offers some concrete routing: "a long, busy scene renders with preview false", "video_cost says it first" for pricing, and "GET /api/agents/jobs/<job> (or the MCP tool job)" for polling. However, it never states when to prefer video_render over siblings such as video_still or video_check, so the guidance is implied rather than explicit.

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