Skip to main content
Glama

stitch_screen_audit

Audits a Stitch-captured HTML screen or file with 25 WCAG 2.1 checks, 35+ anti-slop gate checks, and a 6-axis craft critique to surface accessibility and design quality issues.

Instructions

Run a unified audit on a Stitch-captured HTML screen or file. Executes 25-check WCAG 2.1 static analysis, 35+ gate anti-slop checks, and 6-axis craft critique.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "stitch_screen_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
genreNoDesign genre for scoped anti-slop checks (default: avant-garde)
filePathNoPath to a captured HTML file (e.g. .stitch/captured-dom.html)
screenHtmlNoFull HTML content of the captured screen

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.0.1

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations at all, the description carries the full burden, but it does contribute one meaningful behavioral cue: 'static analysis' implies a read-only, non-mutating pass. It does not say whether a report is written anywhere, what happens if both filePath and screenHtml are supplied, or that all three parameters are optional and what occurs with none provided.

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?

Two tight sentences with the core action front-loaded and the check inventory second; nothing is padded. 'Unified' is slightly redundant with the enumerated checks but not wasteful.

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 a 3-param, all-optional audit with no output schema, the description covers what runs and on what, which is most of what an agent needs to invoke it. The remaining gap is that it never indicates what comes back (scores, findings list, pass/fail) nor how the optional inputs interact.

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 phrase 'HTML screen or file' loosely maps to the screenHtml/filePath duality, but the description adds no guidance on which source takes precedence or how genre scopes the checks beyond what the schema already says.

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 gives a specific verb and target ('Run a unified audit on a Stitch-captured HTML screen or file') and enumerates the three audit batteries (25-check WCAG 2.1, 35+ anti-slop gates, 6-axis craft critique), so the intent is unambiguous. It never mentions the closely named sibling 'design_audit', so an agent cannot tell the two apart from the text alone.

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?

Usage is only implied through the input scoping: it applies to Stitch-captured HTML screens or files. There is no explicit when-to-use vs. when-not guidance, no mention of design_audit or detect_genre/evaluate_style as alternatives, and no prerequisites stated.

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