Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Multiply an ad

multiply_ad

Create multiple variants of a winning video ad by changing character, outfit, location, and objects while preserving the original cut, camera motion, pacing, and audio.

Instructions

MULTIPLY a winning video ad into N variants: each gets a NEW character, outfit, location and/or objects while the cut, the camera motion, the pacing and the ORIGINAL AUDIO stay exactly as they were (that is what made the ad work), and any burned-in captions are removed. Pass the source video URL (a previous render, a job result, list_library, or the top performer from post_performance / meta_insights). HOW: the source video itself DRIVES each variant (motion transfer from one image-edited opening frame), so every variant comes back the SAME LENGTH as the source with the same cut, the same performance and the original audio — only the person, outfit, set and props change. Sources up to 30 seconds work as they are; longer ones are refused for free with the way out (trim it first: post_edit with ops [{op:'trim', start:0, end:30}] — clip_video is the AI highlight clipper, not a trim). Returns the plan and ONE JOB PER VARIANT — call get_job on each until it reports done; do not describe a variant before its URL arrives. Cost is quoted per variant in the reply (use dryRun:true to see the plan and the quote without rendering). Regions: pass regions:['Berlin','Tokyo'] to restyle variants per market; translation is a separate, explicit step — dub_video on a finished variant. change is what should change, in the user's own words ('older women', 'winter streets', 'swap the mug for our bottle'): every variant applies it and the variants still differ around it; a part of it about the voice, words, language, music, length or captions cannot change here, and the reply says so and names the tool that can.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
axesNowhat to vary: character, outfit, location, objects (default all four), or your own, e.g. "season"
countNohow many variants, 1-12 (default 6)
notesNoanything the variants must respect, e.g. "keep it women 25-40", "no gyms"
videoYesthe source video URL
changeNowhat should change, in the user's own words, e.g. 'older women, winter streets'; every variant applies it (omit to let the variants vary freely)
dryRunNotrue = return the plan and the quote, render nothing
regionsNomarkets to restyle for, one or more variants each, e.g. ["Berlin","Tokyo","São Paulo"] — visuals only; audio is never translated here

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.366
    • addedInput schema / properties / change
      Added value: +{
+  "description": "what should change, in the user's own words, e.g. 'older women, winter streets'; every variant applies it (omit to let the variants vary freely)",
+  "type": "string"
+}
  2. Changed2 schema fields changedv0.1.285
    • changedInput schema / properties / axes / description
      Previous value: -"which axes to vary (default: all four)"New value: +"what to vary: character, outfit, location, objects (default all four), or your own, e.g. \"season\""
    • removedInput schema / properties / axes / items / enum
      Removed value: -[
-  "character",
-  "outfit",
-  "location",
-  "objects"
-]
  3. Addedv0.1.189

TDQS

A4.8/5.0
Behavior5/5

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

Adds substantial context beyond annotations: length/cut/audio preservation, caption removal, the 30-second limit with a free refusal, per-variant cost quoting, dryRun behavior, and the async job-per-variant pattern requiring get_job. Annotations (non-idempotent, open-world, not destructive) are consistent and supplemented.

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?

Long but front-loaded with the core behavior, and most sentences carry operational value (limits, cost, job flow, sibling routing). Some density and repeated framing ('that is what made the ad work', restated preservation) cost it a point.

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?

No output schema exists, and the description compensates fully by explaining the return ('the plan and ONE JOB PER VARIANT — call get_job on each until done') plus cost quoting and the dryRun preview path. Nothing an agent needs to invoke it correctly is missing.

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 100%, so the baseline is 3, but the description adds real semantics: `change` applies to every variant while variants still differ, and content about voice/words/language/music/length/captions cannot change here; `regions` restyles visuals only with audio never translated. These go beyond the schema text.

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 ('MULTIPLY a winning video ad into N variants') and precisely defines the scope of change (character/outfit/location/objects) versus what is preserved (cut, camera motion, pacing, original audio). It explicitly distinguishes itself from siblings by naming clip_video and post_edit as different tools.

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?

Explicit about when to use it, where the source URL comes from (previous render, job result, list_library, top performer from post_performance/meta_insights), and what to do when input exceeds 30s ('trim it first: post_edit... clip_video is the AI highlight clipper, not a trim'). It routes translation to dub_video.

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