Skip to main content
Glama

Audit Accessibility

audit_accessibility

Audit a design image against WCAG 2.2 to identify contrast, tap-target, text-size, focus, label, and color-only issues, with suggested fixes and a scored report.

Instructions

Audit a design image against WCAG 2.2: exact contrast ratios with suggested fixes, plus tap targets, text size, focus, labels and color-only meaning. Returns a scored report.

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": {
      "image": "<image>"
    },
    "name": "audit_accessibility"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageYesLocal file path or http(s) URL of the design image

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.5/5.0
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 burden. It does disclose the central behavioral trait that the output is 'a scored report' and that fixes are suggested, but it says nothing about image size/format limits, failure handling for unreachable URLs, or how long a full audit takes — meaningful gaps for an unannotated tool.

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 front-loaded sentences, zero filler: the standard and scope come first, the checklist second, the return value last. Every clause carries information about coverage an agent could not infer from the name.

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 single-parameter tool with no annotations and no output schema, the description should say more about what the 'scored report' contains (per-criterion scores? pass/fail? overall score?) and any input constraints. The checklist of audited categories helps, but the return contract and input limits remain vague.

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?

Only one parameter exists and schema coverage is 100%, with the schema already explaining 'Local file path or http(s) URL'. The description's 'design image' phrasing adds no format, dimension, or resolution constraints beyond that, so it hits the baseline rather than adding value.

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?

States a specific verb and resource ('Audit a design image') plus the exact standard (WCAG 2.2) and enumerates what is checked: contrast ratios with fixes, tap targets, text size, focus, labels, color-only meaning. This lets an agent separate it from a narrow sibling like check_contrast, though no sibling is named explicitly.

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: the WCAG framing and 'design image' scope suggest it is the full-audit entry point rather than a single-check tool, but there is no explicit 'use this when...' or 'do not use for...' statement and no pointer to alternatives such as check_contrast or audit_site.

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