Skip to main content
Glama

Digital Maker AI

by io.github.digitalmakerai
OverviewDiscussionsAdmin

generate_image

Generate a YouTube thumbnail, channel banner, logo, product mockup or general image. Counts against the monthly image allowance (Pro 200, Premium 500, Ultimate 1,000 a month; extra images can be bought as image packs) and saves to the user's library. Make one image per request the user actually wants; never loop to produce dozens of variations unless they asked for that many. At most 100 images an hour go through this connector. Set image_type: it controls the shape of the result, and getting it wrong produces something the user cannot actually use. To feature one of the user's saved characters OR one of their made AI presenters in the image (a profile picture, logo, banner or thumbnail with the presenter's face), pass character with their name and the face will match. To CREATE a reusable character rather than use one, use create_character instead. To make an AI PRESENTER or AVATAR (a talking on-screen host for videos), do NOT use this: use draw_presenter, which draws them in the right pose and leads to make_presenter.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesWhat the image shows. Visual and specific. Include on-image text exactly as it should appear. Describe content only: the shape, aspect ratio and framing are handled automatically from image_type, so do not ask for dimensions here.
characterNoName of a saved character or a ready AI presenter to feature in the image, so the person in it is recognisably them. Optional. Must already exist: use list_characters or list_presenters to check.
image_typeNoyoutube_thumbnail is 16:9 widescreen. youtube_banner is real 2560x1440 YouTube channel art with the whole design kept inside the area visible on every device (TV, desktop, phone). logo is square and built to stay readable as a small avatar. mockup puts the product on a pure white background for a shop listing. general applies no shape rule. Defaults to general.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses quota costs (Pro 200 / Premium 500 / Ultimate 1,000 per month), an hourly rate limit (100 images/hour), and that results persist to the user's library. It omits failure/moderation behavior and whether the image is returned inline versus only saved, keeping it short of a 5.

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?

Purpose, quota, rate limit, and the image_type warning are front-loaded before the sibling routing, which is the right order. It is a long description, but nearly every clause carries actionable information; a couple of sentences (quota enumeration, the looping warning) run long and could be tightened.

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?

For a 3-parameter generation tool with no output schema, the description supplies everything needed: cost, limits, persistence to library, the critical image_type constraint, character requirements, and explicit sibling routing. 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 description coverage is 100%, so the baseline is 3. The description goes beyond the schema by warning that image_type 'controls the shape of the result' and that choosing wrong yields unusable output, and by clarifying that character must already exist and that its face will match. That is genuine added meaning over the enum docs.

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 concrete verb+resource ('Generate a ... image') and immediately enumerates the artifact types it covers. It also explicitly demarcates itself from siblings, naming create_character and draw_presenter as the correct tools for adjacent tasks, so an agent can disambiguate without opening a schema.

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?

Gives explicit when/when-not routing: use create_character to CREATE a reusable character, use draw_presenter for AI presenters/avatars, and use this tool only when featuring an existing saved character. It even constrains call volume ('never loop to produce dozens of variations unless they asked').

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

All Digital Maker AI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources