Skip to main content
Glama

accessibility-ai

by io.github.groundlogic-ai-source

scan_accessibility

Read-only

Scans a URL for WCAG 2.1 accessibility violations using DOM analysis (axe-core) and visual AI (Claude Vision). Returns structured violation data and a scan_id for use with other tools.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL to scan for accessibility violations
max_pagesNoMaximum pages to scan when scan_depth is full_site
scan_depthNoWhether to scan a single page or crawl the full site (max 10 pages)single_page
vision_modeNoVision analysis depth. 'standard' runs one Claude Vision pass on the full page (fast, default). 'thorough' analyzes the page section-by-section with a two-pass consensus to reduce false positives (slower, more API calls; applied to the first page only).standard
anthropic_api_keyYesYour Anthropic API key (used only for this request, never stored)

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's disclosure of returning data and scan_id is adequate but not rich. No mention of rate limits or other side effects beyond what annotations convey.

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 well-structured sentences with no redundancy. Front-loaded with core purpose and method, followed by key output details.

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?

Given 5 parameters, full schema coverage, and no output schema, the description covers the tool's purpose, methods, and output. Could mention more about scan_id usage, but overall complete for a scan tool.

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 coverage is 100% with clear descriptions for each parameter. The description does not add semantic information beyond what the schema provides, so baseline score applies.

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 clearly states the tool scans a URL for WCAG 2.1 violations using specific methods (axe-core, Claude Vision) and returns structured data and a scan_id. It distinguishes from siblings like 'generate_fixes' and 'generate_vpat' which are post-scan tools.

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 description implies usage as a first step by mentioning scan_id for use with other tools, but does not explicitly state when to use versus alternatives or when not to use.

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

All accessibility-ai toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: scanning, generating fixes, generating VPAT reports, and re-verifying. No overlap in functionality.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (scan_accessibility, generate_fixes, generate_vpat, re_verify). The naming is predictable and uniform.

Tool Count5/5

With 4 tools covering the core workflow of scanning, fixing, reporting, and re-verification, the count is well-scoped and no tools feel redundant or missing.

Completeness5/5

The tool surface covers the full lifecycle: scan accessibility issues, generate fixes, re-verify after fixes, and generate a VPAT report. No obvious gaps for the domain.

Resources