Skip to main content
Glama

design_audit

Audits design work via WCAG 2.1 accessibility checks, anti-pattern slop gates, 6-axis quality critique, or preflight token and stack scans, so issues surface before shipping.

Instructions

Audit design work. Select action: accessibility (25-check WCAG 2.1), slop (35-gate anti-pattern check), critique (6-axis quality score), or preflight (scan an existing project's design tokens and stack).

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": {
      "action": "<action>"
    },
    "name": "design_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
htmlNoFull HTML required for accessibility
genreNoGenre for scoped slop gateseditorial
actionYesAudit mode
contentNoHTML/CSS required for slop and critique
project_pathNoProject root for preflight (defaults to MCP root)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.0.1

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It usefully discloses the rigor of each mode (check counts, gate counts, axis counts), but says nothing about whether the tool is read-only, whether preflight touches or writes project files, or what form the audit report takes. For a multi-mode analysis tool with zero annotation coverage, these are meaningful omissions.

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

Conciseness5/5

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

Two sentences, front-loaded with the core purpose, then a compact parenthetical breakdown of every mode. No filler and no repetition of schema content.

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?

The tool has five parameters, four distinct modes, no annotations, and no output schema, which raises the disclosure bar. The description covers mode selection well but leaves the return shape and side-effect profile unexplained, which matters especially for 'preflight', a mode that reads an external project.

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 100%, so the baseline is 3. The description does add real meaning to the 'action' enum, whose schema description is only 'Audit mode', by explaining what each of the four modes actually performs. It adds nothing about genre scoping or which inputs pair with which mode beyond what the schema already states.

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 description opens with a specific verb and resource ('Audit design work') and immediately enumerates four concrete audit modes with their depth (25-check WCAG 2.1, 35-gate anti-pattern check, 6-axis score, token/stack scan). An agent knows exactly what this tool does. It stops short of naming how it differs from near-neighbors like stitch_screen_audit or evaluate_style, so it falls short of 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

By labeling each action, the description effectively tells the agent which mode to pick for which goal (accessibility compliance vs anti-pattern slop vs qualitative critique vs project scan). That is clear in-tool routing. There are no exclusions or guidance on when to prefer a sibling audit tool instead, so it does not reach 5.

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