Skip to main content
Glama

Plunder & Riffle Meme Engine

Make a meme or ad

generate_ad_creative

One ad creative in one language, in the format you pass (omitted = single meme). Returns a TEMP PAGE preview (not an MP4), PNG URLs (adAssets, media_url), post_copy and a referralUrl. Costs the format's list credits; BYOK: $0.01. Optional motion_style (a banked style id from list_motion_styles) leads a moving format's motion design with that style's full director prompt — same price.

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": {
      "brief": "<brief>"
    },
    "name": "generate_ad_creative"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoYour referral code (returned in referralUrl).
brandNoBrand key (default house brand).
briefYesWhat the ad is about: product, hook, angle.
offerNoOffer or call to action to work into the creative.
sizesNoPNG sizes (default all). Not the creative `format`.
formatNoCreative format — set it to what was asked; omitted = single meme. iMessage / text thread → "hybrid"; carousel / slideshow → "carousel"; hot take → "hottake"; confession → "confession"; single meme / image → "image".
audienceNo
languageNoDefault English.
allFramesNoExport every slide (max 10). Default true for carousel/hybrid.
brandProfileNoAd-hoc brand voice, overrides `brand`: name, voice (≤1000), hashtag, token, ctaStyle {tone, action (no URL), linkPlacement first-comment|caption, avoid[], examples[]}.
motion_styleNoOptional banked motion-design style id (see list_motion_styles). For the moving formats (carousel, hybrid) the style's full director prompt leads the generation instead of the automatic style pick-list. Same price as the call without it. Ignored by still formats.
includeAssetsNoRender PNGs and return URLs (default true; false for single memes).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations only declare destructiveHint=false, so the description carries most of the load and does it well: it discloses that output is a TEMP PAGE preview, not an MP4 (implying a separate request_mp4 step), what fields come back, the credit cost model plus BYOK pricing, and that motion_style is ignored by still formats. Failure modes and whether the temp page expires are not covered.

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 the core action and return shape, then cost, then the optional motion_style nuance. Dense but every sentence carries information; the only mild cost is the long dash-heavy sentence about motion_style.

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 12-parameter generation tool with no output schema and minimal annotations, the description covers return artifacts, cost, and the format/motion_style interaction well. Gaps remain around failure/retry behavior and how long the TEMP PAGE preview persists.

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 92%, so the baseline is 3. The description reinforces two subtle points — omitted `format` means a single meme, and `motion_style` only affects moving formats — but these are already stated in the schema, so it adds little genuinely new parameter meaning.

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 specific verb and resource ('one ad creative in one language') and ties the output to the `format` argument, so an agent knows exactly what it produces. It does not distinguish itself from the many sibling create_* tools (create_before_pitch, create_infomercial, create_news), leaving sibling selection ambiguous.

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?

Provides solid format-selection guidance in the description and schema (iMessage thread → hybrid, carousel → carousel, hot take → hottake), and points to list_motion_styles for style ids. But there is no guidance on when to call this versus the numerous other creation siblings, which is the harder selection decision an agent faces here.

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