Skip to main content
Glama
Design Atlas MCP

Design Atlas MCP

by Tradelord223

apply_reference_detail

Read-onlyIdempotent

Applies an inspected design reference to existing HTML by matching selectors, then returns original markup, matched selectors, and runnable integration files.

Instructions

Apply an inspected reference to supplied existing HTML. For aperture-hero-reveal pass hero with a host selector, existing media selector and selected treatment. For anchored-field-note pass notes with source text and existing focusable targets. Returns original markup, matched selectors and runnable integration files.

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": {
      "referenceId": "<referenceId>",
      "html": "<html>"
    },
    "name": "apply_reference_detail"
  }
}

Input Schema

NameRequiredDescriptionDefault
heroNo
htmlYes
notesNo
appearanceNo
referenceIdYes
referenceVersionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real value beyond that by disclosing the return payload (original markup, matched selectors, runnable integration files) and clarifying that the input HTML is returned rather than mutated. It omits edge-case behavior such as what happens when a selector matches zero or more than the expected number of elements.

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 front-loaded sentences with no filler: purpose first, then variant-specific requirements, then return values. The parallel "For X pass Y" construction is easy to scan. Slightly dense with domain jargon ("treatment", "runnable integration files") that is never unpacked.

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?

For a tool with two nested variant schemas, no output schema and zero parameter descriptions, the description covers purpose, variant routing, and return contents, which is the core. It still leaves the agent guessing about appearance/referenceVersion, expectedCount behavior, and what happens on selector mismatch, so it is adequate but not complete.

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 0% and there are six parameters including two nested variant objects, so the description carries the burden. It does explain the meaningful shape of the hero object (hostSelector, mediaSelector, treatment) and the notes object (source text, focusable targets), which is the hardest part to infer. It says nothing about appearance, referenceVersion, duration, or expectedCount, leaving several parameters undocumented in both places.

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?

"Apply an inspected reference to supplied existing HTML" gives a specific verb (apply) and resource (reference), and the per-referenceId sentences distinguish the two variants (aperture-hero-reveal vs anchored-field-note) so an agent can tell which one it is invoking. It stops short of explicitly contrasting with siblings like get_reference_guide or remix_inspirations, which is why it isn't a 5.

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?

The phrase "inspected reference" implies a prior inspection step and the two "For X pass Y" sentences route the agent between reference variants. However, there is no explicit when-to-use / when-not-to-use statement, no stated prerequisite tool, and no named alternative for cases where the agent should remix or fetch a reference instead.

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