Skip to main content
Glama

webability

by io.github.snayyar00
OverviewDiscussionsAdmin

Compare two accessibility scans

diff_scan
Read-onlyIdempotent

Compare two scans of the same page and report what changed: fixed[] (in the baseline, gone now), new[] (regressions — not in the baseline, present now), remaining[] (still there). Page-level complement to verify_fix (one element). Baseline is a scan_history id (baselineId, local installs) or a live scan of baselineUrl; current is url (scanned live now) or another history id (currentId). Findings are matched by issue id (rule + element), so a changed class/id on a fixed element reads as fixed AND new — check new[] before calling it a regression. Typical loop: scan_page → edit → diff_scan(baselineId=, url=) → confirm new[] is empty. 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
urlNoURL to scan now as the CURRENT side (deployed, staging, or http://localhost:3000). Omit when passing currentId.
wcagNoOnly these WCAG criteria. A prefix selects the whole guideline ("1.4") or principle ("2").
levelNoHighest WCAG conformance level to report. Default "AA" — Level AAA criteria are not reported. Pass "AAA" to include them (naming one AAA criterion in `wcag`, e.g. "3.2.5", also includes it).
rulesNoOnly these rule ids (WebAbility type such as "missing_alt" or axe rule id such as "image-alt"). See get_rules.
formatNo"compact" prints one line per element with rule metadata once. "json" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count.
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."
viewportNoViewport for live scans (default: desktop). Use the same viewport the baseline used.
currentIdNoscan_history id to use as the CURRENT side instead of scanning `url`
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.
minImpactNoOnly findings at this severity or above (critical > serious > moderate > minor)
baselineIdNoscan_history id of the BASELINE scan (local installs only)
baselineUrlNoScan this URL live as the baseline (e.g. production) — use when there is no stored baseline
rootSelectorNoCSS selector to limit live scans to (optional)
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. Changed1 schema field changed
    • addedInput schema / properties / level
      Added value: +{
+  "description": "Highest WCAG conformance level to report. Default \"AA\" — Level AAA criteria are not reported. Pass \"AAA\" to include them (naming one AAA criterion in `wcag`, e.g. \"3.2.5\", also includes it).",
+  "enum": [
+    "A",
+    "AA",
+    "AAA"
+  ],
+  "type": "string"
+}
  2. Changed1 schema field 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"
-}
  3. Changed2 schema fields changed
    • changedInput schema / properties / format / description
      Previous value: -"\"compact\" prints one line per element with rule metadata once — far fewer tokens than the default JSON. Default json."New value: +"\"compact\" prints one line per element with rule metadata once. \"json\" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count."
    • changedInput schema / required
      Previous value: -[
-  "context",
-  "llm_model"
-]New value: +[]
  4. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantive traits beyond them: matching is done by issue id (rule + element), a changed class/id can make a fixed element read as both fixed AND new, and the hosted server refuses localhost and requires a tunnel secret. These are non-obvious behaviors an agent must know to interpret results correctly.

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?

Front-loaded with the return shape, then the semantic caveat, then the usage loop, then the host constraint — a logical order where each block earns its place. It is dense and long, and some parameter commentary (e.g. tunnel_secret) partially duplicates the schema, but nothing is wasted or misleading.

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?

Although there is no output schema and 14 parameters, the description enumerates the returned keys, explains the four baseline/current parameters, and covers the deployment constraints. An agent has everything needed to call it and interpret the result 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, but the description adds a conceptual model the schema lacks: baseline is a history id or a live URL, current is a live URL or another history id, and the viewport should match the baseline. This clarifies the four-way relationship among url/currentId/baselineId/baselineUrl beyond the individual field docs.

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 and resource (compare two scans of the same page) and enumerates the exact output shape (fixed[], new[], remaining[]). It explicitly positions itself against a sibling — 'Page-level complement to verify_fix (one element)' — so an agent can distinguish the two without reading either schema.

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?

Gives an explicit when-to-use loop (scan_page → edit → diff_scan → confirm new[] is empty), names the alternative (verify_fix), and describes the baseline/current source combinations. It also states a hard usage constraint (localhost/private addresses refused on this hosted server) with two concrete workarounds.

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