Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Make template ad

make_template_ad

Create image or video ads from preset templates or custom HTML/CSS, including carousels, branding, and optional music.

Instructions

An ad or post rendered from HTML: no AI model, ~30s, a couple of credits. Presets are SHORTCUTS; 'custom' is YOUR OWN design as config.html (+ css), so no layout, type, colour or motion is 'unsupported'. custom: { html, css?, size? ('9:16' default | '4:5' | '1:1' | '16:9' | any 'W:H' | {w,h} px), durationSeconds? (1-60 = VIDEO; CSS/SVG animation and are frame-stepped, scripts stripped), slides?:[{html, css?}] (2-35 = carousel) }; {{logo}} {{brandName}} {{domain}} {{accent}} fill from the brand; images and fonts load by https URL; notes[] lists what failed to load. YOU author preset copy: short, casual, believable, finished phrases within budget. The preset ids — slideshow, imessage-chat, chatgpt-chat, apple-notes, value-prop, static-mockup, airdrop-carousel, app-ui-tour, imessage-cascade, photo-grid, vignette, kinetic-type, myth-vs-fact, carousel — and each one's fields are listed on config. config.music on a VIDEO: omit and the format gets a music bed from our library, matched to its mood and free, whenever the library is stocked (hermoso_capabilities hasMusic); with none on file the video carries only its own sound effects, and the reply says so. 'off' for silence, or any words (a mood or a description) to compose a bed to them (a flat music fee, in hermoso_capabilities). Image URLs may be any public URL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
configYesMUST include config.template: 'custom' or a preset id, plus its fields. PRESETS: 'slideshow' (IMAGES, TikTok photo mode / Reels 1080x1920, or size:'4:5' feed carousels; no branding): { slides:[{text, sub?, image?, blur?, background?, position?}] (2-35; words never rewritten), style? ('tiktok-classic'|'clean-minimal'|'note-style' or a look in words), textStyle?, video?:true (+ an MP4, which takes config.music like any video) }; 2 credits, +1 per slide past 5, +2 for the MP4. 'imessage-chat' (VIDEO ~15s): { thread:{contactName, messages:[{from:'them'|'me', text?, product?:{image,title,domain}}]}, theme?, endCard }. 'chatgpt-chat' (VIDEO): { question, answer (may **bold** the brand), productImage?, endCard }. 'apple-notes' (VIDEO): { title, lines[], theme?, endCard }. 'value-prop' (VIDEO ~17s): { hook ≤40ch, claims[3-5 ≤34ch], productImages[2-3], palette[], endCard }. 'static-mockup' (IMAGE): { style:'imessage'|'notes'|'card', size?:{w,h}, ...fields }. 'airdrop-carousel' (VIDEO): { brandName, products:[{image, title?}] (3-16), endCard }. 'app-ui-tour' (VIDEO): { hook?, appName, iconImage?, beats:[{screenImage, caption}] (2-6), endCard }. 'imessage-cascade' (VIDEO): { notifications:[{sender, text}] (4-8), backgroundImage?, endCard }. 'photo-grid' (VIDEO): { title?, photos:[{image, label?}] (4-9), endCard }. 'vignette' (VIDEO): { hook, lines[2-4 ≤40ch], heroImage, endCard }. 'kinetic-type' (VIDEO, own SFX): { phrases[3-6 ≤34ch], productImages?[≤4], endCard }. 'myth-vs-fact' (VIDEO with a real VOICEOVER, small extra charge): { pairs:[{myth ≤50ch, fact ≤60ch}] (2-4; [brackets] accent), endCard }, real truths only. 'carousel' (IMAGES, 5-10 branded 1080x1080): { cover:{hook?, title}, slides:[{headline, support?, stat?:{value, label}}] (3-8), cta:{headline, cta?, domain?}, productImage?, logo? }. endCard = { headline, cta, domain?, logo?, color? }; palette and fontStack optional.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.409
    • changedInput schema / properties / config / description
      Previous value: -"MUST include config.template: 'custom' or a preset id, plus its fields. PRESETS: 'slideshow' (IMAGES, TikTok photo mode / Reels 1080x1920, or size:'4:5' feed carousels; no branding): { slides:[{text, sub?, image?, blur?, background?, position?}] (2-35; words never rewritten), style? ('tiktok-classic'|'clean-minimal'|'note-style' or a look in words), textStyle?, video?:true (+ an MP4) }; 2 credits, +1 per slide past 5, +2 for the MP4. 'imessage-chat' (VIDEO ~15s): { thread:{contactName, messages:[{from:'them'|'me', text?, product?:{image,title,domain}}]}, theme?, endCard }. 'chatgpt-chat' (VIDEO): { question, answer (may **bold** the brand), productImage?, endCard }. 'apple-notes' (VIDEO): { title, lines[], theme?, endCard }. 'value-prop' (VIDEO ~17s): { hook ≤40ch, claims[3-5 ≤34ch], productImages[2-3], palette[], endCard }. 'static-mockup' (IMAGE): { style:'imessage'|'notes'|'card', size?:{w,h}, ...fields }. 'airdrop-carousel' (VIDEO): { brandName, products:[{image, title?}] (3-16), endCard }. 'app-ui-tour' (VIDEO): { hook?, appName, iconImage?, beats:[{screenImage, caption}] (2-6), endCard }. 'imessage-cascade' (VIDEO): { notifications:[{sender, text}] (4-8), backgroundImage?, endCard }. 'photo-grid' (VIDEO): { title?, photos:[{image, label?}] (4-9), endCard }. 'vignette' (VIDEO): { hook, lines[2-4 ≤40ch], heroImage, endCard }. 'kinetic-type' (VIDEO, own SFX): { phrases[3-6 ≤34ch], productImages?[≤4], endCard }. 'myth-vs-fact' (VIDEO with a real VOICEOVER, small extra charge): { pairs:[{myth ≤50ch, fact ≤60ch}] (2-4; [brackets] accent), endCard }, real truths only. 'carousel' (IMAGES, 5-10 branded 1080x1080): { cover:{hook?, title}, slides:[{headline, support?, stat?:{value, label}}] (3-8), cta:{headline, cta?, domain?}, productImage?, logo? }. endCard = { headline, cta, domain?, logo?, color? }; palette and fontStack optional."New value: +"MUST include config.template: 'custom' or a preset id, plus its fields. PRESETS: 'slideshow' (IMAGES, TikTok photo mode / Reels 1080x1920, or size:'4:5' feed carousels; no branding): { slides:[{text, sub?, image?, blur?, background?, position?}] (2-35; words never rewritten), style? ('tiktok-classic'|'clean-minimal'|'note-style' or a look in words), textStyle?, video?:true (+ an MP4, which takes config.music like any video) }; 2 credits, +1 per slide past 5, +2 for the MP4. 'imessage-chat' (VIDEO ~15s): { thread:{contactName, messages:[{from:'them'|'me', text?, product?:{image,title,domain}}]}, theme?, endCard }. 'chatgpt-chat' (VIDEO): { question, answer (may **bold** the brand), productImage?, endCard }. 'apple-notes' (VIDEO): { title, lines[], theme?, endCard }. 'value-prop' (VIDEO ~17s): { hook ≤40ch, claims[3-5 ≤34ch], productImages[2-3], palette[], endCard }. 'static-mockup' (IMAGE): { style:'imessage'|'notes'|'card', size?:{w,h}, ...fields }. 'airdrop-carousel' (VIDEO): { brandName, products:[{image, title?}] (3-16), endCard }. 'app-ui-tour' (VIDEO): { hook?, appName, iconImage?, beats:[{screenImage, caption}] (2-6), endCard }. 'imessage-cascade' (VIDEO): { notifications:[{sender, text}] (4-8), backgroundImage?, endCard }. 'photo-grid' (VIDEO): { title?, photos:[{image, label?}] (4-9), endCard }. 'vignette' (VIDEO): { hook, lines[2-4 ≤40ch], heroImage, endCard }. 'kinetic-type' (VIDEO, own SFX): { phrases[3-6 ≤34ch], productImages?[≤4], endCard }. 'myth-vs-fact' (VIDEO with a real VOICEOVER, small extra charge): { pairs:[{myth ≤50ch, fact ≤60ch}] (2-4; [brackets] accent), endCard }, real truths only. 'carousel' (IMAGES, 5-10 branded 1080x1080): { cover:{hook?, title}, slides:[{headline, support?, stat?:{value, label}}] (3-8), cta:{headline, cta?, domain?}, productImage?, logo? }. endCard = { headline, cta, domain?, logo?, color? }; palette and fontStack optional."
  2. Changed1 schema field changedv0.1.320
    • changedInput schema / properties / config / description
      Previous value: -"MUST include config.template: 'custom' or a preset id above, plus its fields"New value: +"MUST include config.template: 'custom' or a preset id, plus its fields. PRESETS: 'slideshow' (IMAGES, TikTok photo mode / Reels 1080x1920, or size:'4:5' feed carousels; no branding): { slides:[{text, sub?, image?, blur?, background?, position?}] (2-35; words never rewritten), style? ('tiktok-classic'|'clean-minimal'|'note-style' or a look in words), textStyle?, video?:true (+ an MP4) }; 2 credits, +1 per slide past 5, +2 for the MP4. 'imessage-chat' (VIDEO ~15s): { thread:{contactName, messages:[{from:'them'|'me', text?, product?:{image,title,domain}}]}, theme?, endCard }. 'chatgpt-chat' (VIDEO): { question, answer (may **bold** the brand), productImage?, endCard }. 'apple-notes' (VIDEO): { title, lines[], theme?, endCard }. 'value-prop' (VIDEO ~17s): { hook ≤40ch, claims[3-5 ≤34ch], productImages[2-3], palette[], endCard }. 'static-mockup' (IMAGE): { style:'imessage'|'notes'|'card', size?:{w,h}, ...fields }. 'airdrop-carousel' (VIDEO): { brandName, products:[{image, title?}] (3-16), endCard }. 'app-ui-tour' (VIDEO): { hook?, appName, iconImage?, beats:[{screenImage, caption}] (2-6), endCard }. 'imessage-cascade' (VIDEO): { notifications:[{sender, text}] (4-8), backgroundImage?, endCard }. 'photo-grid' (VIDEO): { title?, photos:[{image, label?}] (4-9), endCard }. 'vignette' (VIDEO): { hook, lines[2-4 ≤40ch], heroImage, endCard }. 'kinetic-type' (VIDEO, own SFX): { phrases[3-6 ≤34ch], productImages?[≤4], endCard }. 'myth-vs-fact' (VIDEO with a real VOICEOVER, small extra charge): { pairs:[{myth ≤50ch, fact ≤60ch}] (2-4; [brackets] accent), endCard }, real truths only. 'carousel' (IMAGES, 5-10 branded 1080x1080): { cover:{hook?, title}, slides:[{headline, support?, stat?:{value, label}}] (3-8), cta:{headline, cta?, domain?}, productImage?, logo? }. endCard = { headline, cta, domain?, logo?, color? }; palette and fontStack optional."
  3. Changed1 schema field changedv0.1.285
    • changedInput schema / properties / config / description
      Previous value: -"the template config — MUST include config.template (one of the template ids above) plus that template's fields"New value: +"MUST include config.template: 'custom' or a preset id above, plus its fields"
  4. Changed1 schema field changedv0.1.161
    • changedOutput schema / (root)
      Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "jobId": {
-      "description": "the render job id — poll get_job with this id to resume or inspect",
-      "type": "string"
-    },
-    "model": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "description": "the product-facing label of the model that rendered it"
-    },
-    "raw": {
-      "description": "the raw job result payload (e.g. images[] for carousel template ads)"
-    },
-    "stillRendering": {
-      "description": "true when the render is still in progress — keep polling get_job with jobId",
-      "type": "boolean"
-    },
-    "url": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "description": "the served URL of the finished media (absent/null while still rendering)"
-    }
-  },
-  "type": "object"
-}New value: +null
  5. Addedv0.1.0

TDQS

A3.9/5.0
Behavior5/5

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

Annotations only declare the generic write/open-world/non-idempotent profile; the description adds substantial behavior the annotations don't: ~30s runtime, credit costs per slide and per video, scripts stripped and animations frame-stepped, music-bed fallback logic, and the notes[] failure report. This is exactly the context an agent needs before committing credits.

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 sentence is well front-loaded, but the body is a single dense run-on paragraph of semicolon- and parenthetical-separated clauses that is hard to parse and heavily duplicates the config schema description. Structure and brevity are poor for a definition of this length.

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?

Given a single deeply-nested parameter, no output schema, and high complexity, the description is remarkably complete: it covers custom HTML, all preset ids and fields, size/duration constraints, music behavior, branding placeholders, and failure reporting. An agent has everything needed to construct a valid config.

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 description coverage is 100% and the config schema itself carries the preset breakdown, so the baseline is 3. The prose nonetheless reinforces and disambiguates semantics (default size '9:16', durationSeconds 1-60 implying VIDEO, slides 2-35 implying carousel, custom html/css/size shape), adding usable meaning on top of the structured field.

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 concrete verb+resource ('An ad or post rendered from HTML') and immediately differentiates the mechanism from AI generation with 'no AI model, ~30s, a couple of credits'. An agent can tell this is a template/HTML renderer rather than a generative tool, though it never explicitly names which siblings (render_ad, generate_video) it replaces.

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?

It clarifies that presets are shortcuts and 'custom' is the author's own design, and it enumerates every preset id, which helps selection. However, it gives no explicit when-to-use-this-vs-alternative guidance against the many adjacent generation tools, leaving that routing to inference.

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