Skip to main content
Glama

Create meme

create_meme

Creates a meme from a topic and template selection. Costs 10 credits. Starts a background job; returns a project id for wait_for_image_project. Before choosing settings, read get_account_info and the current parameter constraints. A listed model, resolution, duration or count is not necessarily available together or on this account. Preserve explicit requirements and all supplied inputs; explain a genuine block instead of submitting an incompatible request. Account balance alone does not prove a request is affordable.

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": {
      "style": "<style>"
    },
    "name": "create_meme"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe name of the meme.
styleYesMeme topic, template and whether to search the web for content.

Output Schema

NameRequiredDescriptionDefault
idYesUnique ID of the image. Use it with the [Get image Project API](https://docs.magichour.ai/api-reference/image-projects/get-image-details) to fetch status and downloads.
credits_chargedYesThe amount of credits deducted from your account to generate the image. We charge credits right when the request is made. If an error occurred while generating the image(s), credits will be refunded and this field will be updated to include the refund.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / style / description
      Added value: +"Meme topic, template and whether to search the web for content."
  2. Changed3 schema fields changed
    • changedInput schema / properties / style / properties / template / description
      Previous value: -"Select a random meme template."New value: +"To use our templates, pass in one of the enum values."
    • changedInput schema / properties / style / properties / template / enum
      Previous value: -[
      -  "Random"
      -]New value: +[
      +  "Random",
      +  "Drake Hotline Bling",
      +  "Galaxy Brain",
      +  "Two Buttons",
      +  "Gru's Plan",
      +  "Tuxedo Winnie The Pooh",
      +  "Is This a Pigeon",
      +  "Panik Kalm Panik",
      +  "Disappointed Guy",
      +  "Waiting Skeleton",
      +  "Bike Fall",
      +  "Change My Mind",
      +  "Side Eyeing Chloe",
      +  "Woman Yelling at a Cat",
      +  "Success Kid",
      +  "One Does Not Simply",
      +  "Bad Luck Brian",
      +  "Futurama Fry",
      +  "Ancient Aliens",
      +  "Disaster Girl",
      +  "Hide the Pain Harold",
      +  "Distracted Boyfriend",
      +  "Left Exit 12 Off Ramp",
      +  "Running Away Balloon",
      +  "Batman Slapping Robin",
      +  "UNO Draw 25",
      +  "Mocking SpongeBob",
      +  "Boardroom Meeting Suggestion",
      +  "X, X Everywhere",
      +  "Buff Doge vs Cheems",
      +  "Bernie Once Again Asking",
      +  "Roll Safe Think About It",
      +  "Blank Nut Button",
      +  "Epic Handshake",
      +  "Sad Pablo Escobar",
      +  "Inhaling Seagull",
      +  "Surprised Pikachu",
      +  "Always Has Been",
      +  "Scroll of Truth",
      +  "Marked Safe From",
      +  "Y'all Got Any More of That",
      +  "Monkey Puppet",
      +  "Oprah You Get A",
      +  "They're the Same Picture",
      +  "I Bet He's Thinking About Other Women",
      +  "Evil Kermit",
      +  "This Is Fine",
      +  "This Is Where I'd Put My Trophy",
      +  "Anakin Padme Four Panel",
      +  "Who Killed Hannibal",
      +  "Clown Applying Makeup",
      +  "Trade Offer",
      +  "Laughing Leo",
      +  "Sleeping Shaq",
      +  "Megamind Peeking",
      +  "Grandma Finds the Internet",
      +  "Doge",
      +  "American Chopper Argument",
      +  "First World Problems",
      +  "Grumpy Cat",
      +  "SpongeBob Ight Imma Head Out",
      +  "But That's None of My Business",
      +  "Creepy Condescending Wonka",
      +  "Captain Picard Facepalm",
      +  "Hard to Swallow Pills",
      +  "Bell Curve",
      +  "Absolute Cinema",
      +  "You Guys Are Getting Paid",
      +  "Types of Headaches",
      +  "Mother Ignoring Kid Drowning in a Pool",
      +  "Flex Tape",
      +  "Spiderman Pointing at Spiderman",
      +  "Charlie Conspiracy",
      +  "Pawn Stars Best I Can Do",
      +  "0 Days Without",
      +  "Squidward Window",
      +  "Where Monkey",
      +  "Soldier Protecting Sleeping Child",
      +  "They Don't Know",
      +  "Spiderman Triple",
      +  "Two Guys on a Bus",
      +  "Imagination SpongeBob",
      +  "All My Homies Hate",
      +  "You Know I'm Something of a Scientist Myself",
      +  "Anime Girl Hiding from Terminator",
      +  "A Train Hitting a School Bus",
      +  "AJ Styles and Undertaker",
      +  "Three-Headed Dragon",
      +  "Grant Gustin Over Grave",
      +  "Whisper and Goosebumps",
      +  "Scooby Doo Mask Reveal",
      +  "Domino Effect",
      +  "Two Paths",
      +  "I'm the Captain Now",
      +  "Say the Line Bart",
      +  "Star Wars Yoda",
      +  "Grim Reaper Knocking Door",
      +  "Yo Dawg Heard You",
      +  "Gus Fring We Are Not the Same",
      +  "C'mon Do Something",
      +  "Leonardo DiCaprio Cheers"
      +]
    • addedInput schema / properties / style / properties / template / example
      Added value: +"Drake Hotline Bling"
  3. Added

TDQS

A4/5.0
Behavior5/5

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

Annotations already flag non-read-only, non-idempotent, open-world behavior, and the description adds substantial context on top: a 10-credit cost, an asynchronous background job, a returned project id, and the tool to poll next. It also discloses that availability of settings varies by account, which the annotations do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core facts (cost, async job, project id, prerequisite lookup) are front-loaded and useful, but the latter half drifts into generic policy prose about incompatible requests and affordability. The mention of model/resolution/duration/count parameters reads as boilerplate carried over from another tool and dilutes focus.

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 nested-schema creation tool with an output schema, the key agent-facing facts are covered: credit cost, async execution model, returned project id, and the polling sibling. The main gap is that no realistic invocation example is given, and stray references to nonexistent parameters add confusion.

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 100%, including a documented enum for template and a description for name, so the baseline is 3. The description adds little parameter meaning and instead references model, resolution, duration and count — none of which exist in this tool's schema — which can mislead rather than clarify.

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?

The first sentence states a specific verb and resource ("Creates a meme from a topic and template selection"), which is concrete enough to distinguish it from generic image tools. However, it never explicitly contrasts itself with sibling tools like generate_image or edit_image, so differentiation relies on the word "meme" alone.

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 a clear prerequisite ("Before choosing settings, read get_account_info and the current parameter constraints") and warns against submitting incompatible requests, naming the follow-up tool wait_for_image_project. It lacks explicit when-not-to-use guidance or named alternatives for non-meme image generation.

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.