Skip to main content
Glama

var2_create_motion_graphics

Motion graphics with PIXEL-EXACT text: kinetic typography, animated titles, lower thirds, stat counters, logo stings, product / app launch videos, sale and quote cards, type over the user's own footage or photos. Drawn by code (0 % video generation), so words never garble and stay editable. USE THIS (not var2_create_video) when the deliverable is designed TEXT / graphics in motion; use var2_create_video for filmed-looking footage of people, places or scenes. READ var2_motion_catalog FIRST (styles, components, joins, physics). Modes: (1) composition — assemble reusable moments and motivated handoffs into a coherent film; free and deterministic. Search a varied shortlist, preserve coordinated mini-scenes, and inspect exact copy/timing in a free preview; (2) template + params (+ aspect_ratio, brand_kit_id) — preserve an entire requested template; free; (3) brief — the compiler writes the spec; put the exact on-screen words in quotes, one beat per line, plus mood / colors / pace (billed per second); (4) project_id (from any earlier motion result) or a spec you wrote, + instruction — revise it in plain language (billed like a compile); without an instruction, render:true renders it as-is (free). Media: image_urls (logos / photos → image layers, cutouts, frames, chips in the copy), footage_url (video or photo BEHIND the piece). Narration: voice_over {script|dialogue, voice} or voice_asset_id — every spoken phrase lands on screen as it is said; voice_convert re-voices it. Draft first: render:false (default) saves the piece as a draft (project_id, free) and returns warnings and human_summary (every word with its timing) while the user watches it play live in the chat; once they approve (the draft's "Render video" button posts "Looks good - render the final video (project )." - render THAT project), var2_save_motion_graphics { project_id, render: true } queues the MP4 and the chat shows it when done. Free alternatives: var2_preview_motion_graphics (compose or validate a spec) and var2_save_motion_graphics (editable project, optional free render). Template ids and params: var2_motion_catalog. Presets (briefs): kinetic, launch, stats, quote, list, countdown, lower-third, announcement.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "var2_create_motion_graphics"
  }
}

Input Schema

NameRequiredDescriptionDefault
fontNoPreferred font. Hebrew → Rubik / Heebo.
nameNo
specNoA Motion Spec you wrote: revise it with `instruction`, or render it as-is. For a piece a previous call made, pass its project_id instead.
brandNoInline brand: {name, tone, messaging, colors, fonts, logo_url}.
briefNoWhat to make. Exact on-screen words in quotes, one beat per line; plus mood / colors / pace.
colorsNoBrand colors (CSS: #hex / rgb()).
paramsNoTemplate params — var2_motion_catalog {template_id} lists each template's params with defaults and a ready call.
presetNoOptional starting brief (used when `brief` is empty, otherwise ignored).
renderNoDefault false: compile only - the user watches a live draft in the chat and confirms the words. true queues the MP4: only after the user approved the draft (or explicitly asked for the final video).
overlayNotrue = an OVERLAY for video: no background is painted, so on a var2_render_timeline "motion" track the video shows through. Alone it sits on black.
templateNoTemplate id (var2_motion_catalog section=templates). Alone = free instant build; with a brief = skeleton for the compiler.
image_urlsNohttps logos / photos the piece may place.
project_idNoA saved piece (every motion result returns project_id): revise it with `instruction`, or render:true renders it in place.
resolutionNoDefault 1080p.
voice_overNoNarrate first, then animate: script (or dialogue [{text, voice}]) + voice id. auto_tag (default true on v4) adds audio tags. Billed as a dialog.
compositionNo{styleId,seed,beats:[{componentId,params,durationFrames?,physics?,rotation?,scale?,join?}]}. Catalog components/styles/physics/joins define the valid values. One coherent story, varied moments.
footage_urlNohttps video or photo BEHIND the piece.
instructionNoPlain-language change applied to `spec`.
aspect_ratioNoDefault 16:9.
brand_kit_idNoThe user's brand kit.
voice_convertNoRe-voice the narration with another voice id (speech-to-speech keeps the timing and the sync).
voice_asset_idNoAudio asset with word timestamps; the piece is timed to it.
duration_secondsNoOmit to let the compiler fit the copy (usually 5–12s).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations carry only a title, so the description bears the full burden and does: it discloses billing per mode (composition free, template free, brief billed per second, revision billed like a compile), that render:false is the default and saves a draft returning warnings and human_summary, and what overlay=true does (no background painted, sits on black). It also states the determinism guarantee and that text stays editable.

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?

Front-loaded with purpose and the USE THIS / not-that routing before any mode detail, and nearly every clause carries actionable information. The cost is density — the single block packs modes, media, narration, and the draft-render loop without headings, which slows scanning for a 23-parameter tool.

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 23-parameter, zero-required tool with nested objects and no output schema, the description covers the return contract (project_id, warnings, human_summary with word timing) and the approval loop, which is exactly what the missing output schema would otherwise require. Nothing an agent needs to call it or advance to var2_save_motion_graphics is absent.

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 96%, so the baseline is 3, but the description adds genuine cross-parameter semantics the schema cannot express: preset is ignored when brief is present, template alone builds instantly while template+brief becomes a compiler skeleton, and project_id both revises and renders in place. Minor gap: composition's beat/join structure is deferred entirely to the catalog rather than described here.

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 (pixel-exact motion graphics drawn by code, 0% video generation) and enumerates concrete deliverable types: kinetic typography, lower thirds, stat counters, logo stings. It explicitly contrasts itself with the sibling it is not (var2_create_video for filmed-looking footage), so an agent can route without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Gives an explicit use/do-not-use rule against var2_create_video, orders a prerequisite (READ var2_motion_catalog FIRST), and enumerates four mutually exclusive input modes (composition, template+params, brief, project_id/spec+instruction). It also names free alternatives (var2_preview_motion_graphics, var2_save_motion_graphics) and the exact draft-approval-to-final-render workflow.

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