Skip to main content
Glama

CreateHQ Image Studio

creator_cover

An article cover built around a person, with the headline set verbatim: ten layouts, any of 19 languages, four shapes. Send the article, outline or rough notes in article_or_notes (up to 6,000 characters, distilled into a short cover brief before the picture is drawn, at no extra credit cost) and the words for the cover in cover_title. The card exists to keep that face exactly, so send a clear front-facing photo in face_image_1; a cover without one is off-brief. Product or UI shots go in extra_assets_image_2 and keep their place in frame. Up to 3 pictures per call. Costs 2 credits per picture (4 for HD) from the connected account.

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": {
      "article_or_notes": "<article_or_notes>",
      "cover_title": "<cover_title>"
    },
    "name": "creator_cover"
  }
}

Input Schema

NameRequiredDescriptionDefault
qualityNoHD doubles the credit cost.
cover_titleYesSet on the cover verbatim — check every character after the run.
aspect_ratioNo3:4 is the feed cover; 16:9 suits article headers. Default: 3:4.
face_image_1NoA clear, front-facing photo. The same features stay consistent when extra assets are added. Send each file as a data URL (data:image/jpeg;base64,…), up to 1. PNG, JPEG or WebP.
layout_styleNoThe ten layouts from the cover playbook: each sets where the person, the props and the type sit. Expression, background and lettering follow the layout, so there is nothing else to pick. Default: Dark gradient.
cover_languageNoEvery cover word is set in this language. Latin and CJK are the most reliable; Thai, Arabic and Hindi are less so. Default: English.
article_or_notesYesUp to 6000 characters. A text model distils them into a short cover brief before the image model runs; the raw text never reaches it.
extra_assets_image_2NoProduct shots or UI screenshots to place in the cover; the face keeps image 1. Send each file as a data URL (data:image/jpeg;base64,…), up to 2. PNG, JPEG or WebP.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: 2 credits per picture (4 for HD) charged to the connected account, up to 3 pictures per call, a 6,000-character distillation step that costs no extra credits, and an honest reliability caveat that Thai, Arabic and Hindi lettering is weaker than Latin and CJK. It also discloses the face-consistency behavior that governs how extra assets interact with image 1.

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?

It is front-loaded with the core identity and then the inputs, cost and caveats, with no filler sentences. The single dense paragraph and stacked clauses make it heavier to parse than it needs to be, but every sentence carries a fact an agent needs.

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 an 8-parameter generation tool with no annotations and no output schema, it covers inputs, costs, pipeline behavior and quality caveats thoroughly. The one real gap is that with no output schema present, it never says what comes back — an image URL, a file, a job id — which an agent needs in order to chain the result.

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 already 100%, so the baseline is 3; the description earns above that by explaining cross-parameter behavior the schema cannot, notably that cover_title is set verbatim and must be re-checked, that article_or_notes is distilled rather than passed through, and that 1 face image plus 2 extra assets is what the '3 pictures per call' limit refers to.

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 opening sentence names a specific artifact (an article cover built around a person) with concrete scope: ten layouts, 19 languages, four shapes. It is unmistakably not generate_image or pet_holiday_portraits, but it never explicitly contrasts itself with those siblings, leaving that routing inference to the caller.

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 states what to send (article, outline or rough notes), what belongs in each slot (product/UI shots in extra_assets, not the face slot), and gives an exclusion: 'a cover without one is off-brief.' It stops short of naming an alternative tool for cases where no front-facing photo exists.

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