Skip to main content
Glama
Design Atlas MCP

Design Atlas MCP

by Tradelord223

create_image_atlas

Read-onlyIdempotent

Builds a deployable, responsive HTML website from supplied branding, headlines, cover and chapter images, spatial readings and credits, with keyboard-accessible interactions.

Instructions

Build a complete branded, image-led website. Uses the submitted headline, cover photo, spatial readings, chapter images and source credit. Returns one deployable HTML file with its own responsive layout and keyboard-accessible interactions. Use inspect_edition_source to inventory an existing site first.

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": {
      "brand": "<brand>",
      "edition": "<edition>",
      "headline": "<headline>",
      "deck": "<deck>",
      "date": "<date>",
      "accent": "<accent>",
      "image": "<image>",
      "readings": "<readings>",
      "chapters": "<chapters>",
      "sourceUrl": "<sourceUrl>",
      "sourceLabel": "<sourceLabel>"
    },
    "name": "create_image_atlas"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYes
deckYes
brandYes
imageYes
themeNoBrand paper, ink and display type. Paper/ink need 4.5:1 contrast.
accentYes
editionYes
chaptersYes
headlineYes
readingsYes
sourceUrlYesAbsolute HTTPS URL.
sourceLabelYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is consistent with that by framing the result as a returned file rather than a persisted write. Because there is no output schema, the sentence 'Returns one deployable HTML file with its own responsive layout and keyboard-accessible interactions' adds genuine value about the output artifact. It still omits behavioral constraints an agent would want: whether repeated calls with identical input produce identical markup, hard content limits, or failure behavior for invalid images.

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?

Three tight sentences with the core purpose front-loaded, then inputs, then output, then the routing hint. Almost every clause earns its place; the only mild redundancy is listing input ingredients that partially restate the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a high-complexity tool with 12 parameters, nested objects and no output schema, so the description carries a lot of burden. It covers the what and the output shape well, but leaves the meaning of brand, edition, deck, date and the theme contrast constraint undocumented in prose, forcing the agent to rely on a sparse schema.

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 only 17%, so the description has to compensate and it partially does: it maps 'headline', 'cover photo', 'spatial readings', 'chapter images' and 'source credit' onto the headline, image, readings, chapters and sourceUrl/sourceLabel parameters. However, six required parameters (brand, edition, deck, date, accent, theme) get no semantic treatment at all, and concepts like 'spatial readings' remain opaque without opening the nested x/y schema.

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 pairs a concrete verb with a concrete artifact ('Build a complete branded, image-led website'), and the second sentence lists the exact input ingredients that shape the output. An agent can distinguish this generator from siblings like inspect_edition_source or audit_design, though the description never contrasts it with other creation-side tools such as create_brand_kit or apply_reference_detail.

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?

There is one explicit sequencing rule: 'Use inspect_edition_source to inventory an existing site first,' which gives real when-to-use context and names an alternative. Beyond that there are no exclusions (when not to use this, e.g. for updating or auditing an existing site) and no statement of prerequisites such as having brand tokens before generating.

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