Skip to main content
Glama
kinti

a11y-toolkit

by kinti
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

a11y-toolkit: Express WCAG audit

a11y_audit_url
Read-onlyIdempotent

Audit any URL or raw HTML for WCAG 2.2 compliance: get a 0-100 score, 20+ automated checks, and actionable remediation for each issue.

Instructions

Express WCAG 2.2 audit of a URL or an HTML string: 20+ automated signals with a weighted 0-100 score — images without alt (1.1.1), controls without accessible names (4.1.2), form fields without labels (3.3.2), missing autocomplete on user-data fields (1.3.5), click handlers on non-interactive elements (2.1.1), unknown ARIA roles and broken aria-labelledby (4.1.2), duplicated unnamed landmarks, timed meta refresh (2.2.1), missing skip mechanism (2.4.1), lang/title (3.1.1, 2.4.2), heading structure (1.3.1), blocked zoom (1.4.4), captions (1.2.2), autoplay audio (1.4.2), generic/duplicated link text (2.4.4), target=_blank without warning (3.2.5), positive tabindex (2.4.3), aria-hidden on focusable elements, tables without th, duplicate ids, duplicate accesskeys. Each finding includes concrete remediation. Filter, not verdict: automation covers ~1/3 of WCAG; query a11y_criterion for what a criterion means. — Prefer a11y_audit_dom when JS renders the content or contrast/2.5.8/focus matter; use pages for light multi-page sampling.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoURL to fetch and audit
htmlNoraw HTML to audit directly (overrides url)
langNooutput language (en default)
pagesNolight same-domain crawl: audit up to N pages, aggregated by score and recurring signals (default 1, max 20)
timeoutNofetch timeout seconds (30 default)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.12.0
    • changedInput schema / properties / lang / description
      Previous value: -"output language (es default)"New value: +"output language (en default)"
  2. Changed6 schema fields changedv3.3.0
    • addedInput schema / properties / html
      Added value: +{
+  "description": "raw HTML to audit directly (overrides url)",
+  "type": "string"
+}
    • addedInput schema / properties / lang / description
      Added value: +"output language (es default)"
    • addedInput schema / properties / pages
      Added value: +{
+  "description": "light same-domain crawl: audit up to N pages, aggregated by score and recurring signals (default 1, max 20)",
+  "type": "integer"
+}
    • addedInput schema / properties / timeout
      Added value: +{
+  "description": "fetch timeout seconds (30 default)",
+  "type": "number"
+}
    • addedInput schema / properties / url / description
      Added value: +"URL to fetch and audit"
    • removedInput schema / required
      Removed value: -[
-  "url"
-]
  3. First observedv2.3.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context beyond that: it explicitly states the audit is automated, covers ~1/3 of WCAG, is a filter rather than a verdict, and that findings include concrete remediation. This goes beyond the annotations without contradicting them.

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?

The description is long but well-structured: it front-loads the core purpose, then lists specific checks, then adds caveats and routing guidance. Each sentence contributes meaning, though the list of checks could be trimmed without loss. It is more detailed than average but not bloated.

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?

Despite lacking an output schema, the description tells the agent that the tool returns a weighted 0-100 score and that each finding includes remediation. It also explains limitations (covers ~1/3 of WCAG) and when to use sibling tools. For a complex audit tool with 5 parameters, this is sufficient context to invoke it correctly.

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% — every parameter (url, html, lang, pages, timeout) already has a description. The tool description mentions 'URL or an HTML string' and 'pages' for light multi-page sampling, but these add little beyond the schema. Per the rubric, baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Express WCAG 2.2 audit') and resource ('a URL or an HTML string'), enumerates the exact checks covered, and distinguishes itself from siblings by naming a11y_audit_dom and the pages parameter. An agent can immediately tell what this tool does and how it differs from related tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicitly states when to prefer alternatives: 'Prefer a11y_audit_dom when JS renders the content or contrast/2.5.8/focus matter; use pages for light multi-page sampling.' It also notes it is a filter, not a verdict, and recommends querying a11y_criterion for criterion meaning. Clear when-to-use and when-not-to-use guidance.

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

Deploy Server

Other Tools