Skip to main content
Glama
Hermoso

Hermoso

Official

Make a motion graphics video

make_motion_film

Generate motion graphics and animated videos—kinetic typography, logo intros, product launch films, or social cuts—from a brief or images, with a free quote before rendering.

Instructions

MOTION GRAPHICS and ANIMATED VIDEO in one call: kinetic typography (animated text), a logo animation or intro, a product launch film, an animated social cut. Pick it for 'animated video', 'motion graphics', 'kinetic text', 'text animation', 'logo animation', 'logo intro', 'animated explainer' asks. STEPS: without confirm it is a FREE quote that gives both prices (length, the music's tempo; the spec in structuredContent): say both; preview:true is a 1-credit contact sheet of the still version; confirm:true renders. Only the user's or the brand's words appear: never invent a claim, number or review. Full rules: get_instructions({topic:'make_motion_film'}).

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": "make_motion_film"
  }
}

Input Schema

NameRequiredDescriptionDefault
helpNotrue returns the spec language and recipes; renders nothing
hookNoopening line; '*word*' = italic accent
logoNologo image: https, upload_file URL or Library id; default the brand's
moodNomusic and pace
nameNodefault: the saved brand's
sizeNoframe shape: 16:9, 9:16, 1:1 or 4:5
specNothe whole film as JSON, from a quote or a saved film; help:true shows the spec language
briefNowhat the film is about, for the planner
linesNomore short lines, in order
modelNoimage-to-video model id from hermoso_capabilities; default is the best value for short shots
movesNoper scene, what happens in its picture; omit and the planner writes them
musicNo'off' = silent
themeNologo: dark for a light logo
energyNohow much the film keeps moving, 0 to 1; 0 films exactly what is written
imagesNopictures, hero first (https, upload_file URL or Library id)
movingNotrue: one thing physically happens in each picture, filmed by a video model. false: stills moved by a virtual camera, far cheaper. Default true for launch, product, social
recipeNotype, logo, launch, product or social; help:true lists the recipes
confirmNotrue renders the film for real credits; without it you get a free quote
previewNotrue renders a 1-credit contact sheet to approve before the full render
secondsNologo 4-10, others 6-60
taglineNoline shown under the headline or logo
get_costNotrue: return the price only; nothing runs or bills
projectUrlNoa past film's url; returns its saved spec to edit and render again
resolutionNothe moving shots: 720p or 1080p (default) where the model has them
idempotency_keyNochosen once, resent unchanged on retries: the same key never buys twice
expected_creditsNothe get_cost price; refused unbilled if the live price differs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.532
    • addedInput schema / properties / expected_credits
      Added value: +{
      +  "description": "the get_cost price; refused unbilled if the live price differs",
      +  "type": "number"
      +}
    • addedInput schema / properties / get_cost
      Added value: +{
      +  "description": "true: return the price only; nothing runs or bills",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "chosen once, resent unchanged on retries: the same key never buys twice",
      +  "type": "string"
      +}
  2. Changed6 schema fields changedv0.1.519
    • addedInput schema / properties / brief
      Added value: +{
      +  "description": "what the film is about, for the planner",
      +  "type": "string"
      +}
    • addedInput schema / properties / energy
      Added value: +{
      +  "description": "how much the film keeps moving, 0 to 1; 0 films exactly what is written",
      +  "type": "number"
      +}
    • addedInput schema / properties / model
      Added value: +{
      +  "description": "image-to-video model id from hermoso_capabilities; default is the best value for short shots",
      +  "type": "string"
      +}
    • addedInput schema / properties / moves
      Added value: +{
      +  "description": "per scene, what happens in its picture; omit and the planner writes them",
      +  "items": {
      +    "properties": {
      +      "action": {
      +        "description": "the one thing that physically happens, in plain words",
      +        "type": "string"
      +      },
      +      "layer": {
      +        "description": "the picture layer's id, when the scene has several",
      +        "type": "string"
      +      },
      +      "matchNext": {
      +        "description": "the shot ends on the next scene's picture",
      +        "type": "boolean"
      +      },
      +      "scene": {
      +        "description": "scene id",
      +        "type": "string"
      +      },
      +      "still": {
      +        "description": "a picture to animate, when not the one in the scene",
      +        "type": "string"
      +      },
      +      "stillPrompt": {
      +        "description": "a picture to paint first, for a scene with none",
      +        "type": "string"
      +      },
      +      "video": {
      +        "description": "a shot already filmed: kept, and not paid for again",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "scene",
      +      "action"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / moving
      Added value: +{
      +  "description": "true: one thing physically happens in each picture, filmed by a video model. false: stills moved by a virtual camera, far cheaper. Default true for launch, product, social",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / resolution
      Added value: +{
      +  "description": "the moving shots: 720p or 1080p (default) where the model has them",
      +  "type": "string"
      +}
  3. Changed8 schema fields changedv0.1.465
    • addedInput schema / properties / confirm / description
      Added value: +"true renders the film for real credits; without it you get a free quote"
    • addedInput schema / properties / help / description
      Added value: +"true returns the spec language and recipes; renders nothing"
    • addedInput schema / properties / preview / description
      Added value: +"true renders a 1-credit contact sheet to approve before the full render"
    • addedInput schema / properties / projectUrl / description
      Added value: +"a past film's url; returns its saved spec to edit and render again"
    • addedInput schema / properties / recipe / description
      Added value: +"type, logo, launch, product or social; help:true lists the recipes"
    • addedInput schema / properties / size / description
      Added value: +"frame shape: 16:9, 9:16, 1:1 or 4:5"
    • addedInput schema / properties / spec / description
      Added value: +"the whole film as JSON, from a quote or a saved film; help:true shows the spec language"
    • addedInput schema / properties / tagline / description
      Added value: +"line shown under the headline or logo"
  4. Addedv0.1.454

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations, it discloses the economics and side effects: no confirm means a free quote with two prices, preview:true burns 1 credit for a contact sheet, confirm:true does the real render, and content must come only from the user's or brand's words. Those are exactly the facts an agent needs before a non-readOnly, open-world call.

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?

The purpose and routing keywords are front-loaded and the STEPS block sequences the workflow tightly. The all-caps shouting and semicolon chains make it denser than it needs to be, but no sentence is filler.

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 26-parameter tool with nested objects and no output schema, the description covers the decision path, the billing consequences, and the content-safety rule, and it points to get_instructions for full rules. Return-shape details are largely left to the schema's structuredContent reference, which is a minor residual 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 the schema already explains every parameter, and most of the description's parameter talk (confirm, preview, spec) restates that. It adds only the small point that the quote returns both prices and the spec in structuredContent, which is a modest gain over the schema.

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?

The opening states a specific verb and resource ('MOTION GRAPHICS and ANIMATED VIDEO in one call') and enumerates concrete deliverables (kinetic typography, logo intro, product launch film, social cut). It also lists the search phrases that should route here, which separates it from siblings such as make_explainer or make_effect.

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?

It gives explicit selection phrasings ('animated video', 'motion graphics', 'kinetic text') and lays out the quote -> preview -> confirm sequence with the cost at each stage. It stops short of naming sibling tools or stating when a different tool should be chosen instead.

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

Deploy Server

Other Tools