Skip to main content
Glama

webability

by io.github.snayyar00
OverviewDiscussionsAdmin

Validate ARIA in HTML or on a page

check_aria
Read-onlyIdempotent

Validate ARIA attribute + accessible name/role/value usage — in an HTML snippet (html) or on a live page (url), optionally limited to one element and its descendants (selector). Runs axe-core cat.aria and cat.name-role-value rules (aria-* attribute correctness, role validity, required parents/children, aria-hidden-focus, accessible names). Returns violations. A selector that matches nothing, or a page that answers an HTTP error, is an error — never "no violations". Nodes cap at 5 per rule by default — every rule reports nodesTotal + truncated; raise nodeLimit (max 50). NOTE: on this HOSTED server, localhost and private addresses are refused — it runs in our cloud and cannot reach your machine. Two ways to scan a local dev server: run the MCP locally (npx -y @webability/mcp, simplest — nothing leaves the machine), or open a tunnel (webability-tunnel --port 3000) and pass its URL as url together with the printed secret as tunnel_secret.

Input Schema

NameRequiredDescriptionDefault
urlNoLive page to check (pass this or `html`)
htmlNoHTML to test for ARIA correctness (pass this or `url`)
contextNoExplain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
selectorNoOnly report findings on this element and its descendants (e.g. the `selector` from a scan_page issue). ARIA references outside it still resolve.
llm_modelNoThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
nodeLimitNoMax nodes returned per rule (default 5, max 50)
tunnel_secretNoSecret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • removedInput schema / properties / conversation_id
      Removed value: -{
-  "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.",
-  "type": "string"
-}
    • changedInput schema / properties / html / description
      Previous value: -"HTML to test for ARIA correctness"New value: +"HTML to test for ARIA correctness (pass this or `url`)"
    • addedInput schema / properties / selector
      Added value: +{
+  "description": "Only report findings on this element and its descendants (e.g. the `selector` from a scan_page issue). ARIA references outside it still resolve.",
+  "type": "string"
+}
    • addedInput schema / properties / tunnel_secret
      Added value: +{
+  "description": "Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.",
+  "type": "string"
+}
    • addedInput schema / properties / url
      Added value: +{
+  "description": "Live page to check (pass this or `html`)",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "html"
-]New value: +[]
  2. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
-  "html",
-  "context",
-  "llm_model"
-]New value: +[
+  "html"
+]
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial context beyond them: error semantics (an unmatched selector or HTTP error is an error, never 'no violations'), the default per-rule node cap of 5 with nodesTotal/truncated reporting, and the hosted-server refusal of localhost/private addresses with concrete workarounds.

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?

Purpose is front-loaded in the first sentence, followed by rules, output, error semantics, caps, and a clearly delineated NOTE. It is dense and long, but nearly every clause carries operational information; only minor tightening is possible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter, no-output-schema tool, the description covers return shape ('violations'), error conditions, truncation behavior, and the connectivity constraint that would otherwise cause silent failures. An agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema by clarifying selector semantics ('ARIA references outside it still resolve') and reiterating the nodeLimit default/max and tunnel_secret requirement, adding real invocation context.

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?

States a specific verb (Validate) and resource (ARIA attribute + accessible name/role/value usage), and scopes it to an HTML snippet or a live page. It names the exact axe-core rule categories (cat.aria, cat.name-role-value), which distinguishes it from siblings like check_color_contrast and scan_page.

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?

Explains the html-vs-url choice and the selector narrowing case, and even routes the local-dev-server scenario to either running the MCP locally or using a tunnel. It does not explicitly contrast itself against scan_html/scan_page, so the differentiation is implied rather than stated.

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

All webability toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources