Skip to main content
Glama

Create a Silent UGC campaign

autoshort_ugc_create_campaign
Idempotent

Create a silent UGC campaign for your own app by pairing a fictional AI character's reaction with a real screen recording, producing short ad clips ready for social posting.

Instructions

Create a Silent UGC campaign for the user's own app. Silent UGC: 9-12 s silent short marketing clips for the user's OWN app. Scene 1 = one consistent FICTIONAL AI character (realistic, or faceless: hands on a phone / over-the-shoulder / back view) silently reacting with body language and a big hook in the upper third; scene 2 = the app's real screen recording with a short caption. No voice, no audio track (a trending sound is added when posting). Every video carries a visible "AI-generated" note and AI metadata; switch the platform AI label on when posting. Characters come only from a text description (no photo uploads), must be fictional adults (no real or public people, lookalikes or @handles) and non-sexual — the server refuses anything else. Flow: (0) autoshort_ugc_upload_recording (the app screen recording as a public https URL or base64 → recordingAssetId); (1) autoshort_ugc_create_campaign (app name, what it does, a character, recordingAssetId); (2) autoshort_ugc_suggest_hooks; (3) autoshort_ugc_preview ONE hook and show the still to the user; (4) after they approve, autoshort_ugc_render_batch with the hooks they picked; (5) poll autoshort_ugc_get_campaign for the finished videos. Pass characterId to reuse a character, or characterDescription (a fictional adult's look; never a real or public person, a lookalike or a @handle; nothing sexual) plus characterStyle ("face" = realistic fictional character, "faceless" = hands/over-the-shoulder only) to generate one (1 credit, charged before the image is made). recordingAssetId comes from autoshort_ugc_upload_recording (MP4/MOV, 3-60 s, max 50 MB). Free otherwise.

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": {
      "appName": "<appName>",
      "appDescription": "<appDescription>"
    },
    "name": "autoshort_ugc_create_campaign"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNo
appUrlNoPublic URL of the app or its store page.
appNameYes
captionNoScene-2 caption, e.g. "type one idea… get a finished short".
characterIdNo
characterNameNo
appDescriptionYesWhat the app really does. Hooks are written only from this.
characterStyleNoRealistic fictional AI character (default when available) or faceless.
idempotencyKeyNoRetry-safe: a repeat with the same key returns the first answer (replayed: true) and creates nothing.
recordingAssetIdNo
characterDescriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.3.0

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing the credit charge and its timing, the server-side content refusals (non-fictional, lookalike, @handle, sexual), asset constraints (MP4/MOV, 3-60 s, max 50 MB), and the AI-labeling obligation. What it does not disclose is the failure/refund path when character generation is rejected, or what identifiers the response returns for the later polling step.

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, then format rules, then a numbered flow, then parameter notes — a sensible order for scanning. It is dense as a single block and repeats that recordingAssetId comes from autoshort_ugc_upload_recording twice, which costs a little.

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 mutation tool with a credit charge, 11 parameters and no output schema, it covers prerequisites, cost, policy limits and next steps thoroughly. The remaining gap is the return value — the agent is told to poll get_campaign but not what campaign identifier this call hands back.

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 45%, so the description must carry weight; it explains characterId vs characterDescription vs characterStyle and where recordingAssetId comes from, which is the genuinely non-obvious part. However goal, appUrl, characterName and caption are left entirely to the schema, and appDescription's role is only loosely restated, so compensation is partial for an 11-parameter tool.

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?

Opens with a specific verb+resource ("Create a Silent UGC campaign") and immediately defines the artifact: 9-12 s silent clips with a fictional AI character in scene 1 and the app's real screen recording in scene 2. It explicitly scopes it to the user's OWN app, which separates it from the other video-generation siblings.

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?

Provides a numbered end-to-end workflow (steps 0-5) naming each prerequisite tool, so the agent knows this is step 1 and must be preceded by autoshort_ugc_upload_recording and followed by suggest_hooks/preview/render_batch. It also states the branch condition for characterId (reuse) vs characterDescription + characterStyle (generate, 1 credit).

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