Screenshots
Vision models render the page as an image. This is slow and token expensive, so agents use it as a fallback when the structured layers are not available or are ambiguous.
Free Agent Readability Tool
AI agents do not look at your website. They read a machine version of it called the accessibility tree: the browser's stripped down map of roles, names, and states. Google now documents it as one of the three ways agents perceive a page, alongside raw HTML and screenshots. Enter a URL below to score how readable your site is to the agents already browsing on behalf of your customers. Free, no signup required.
Enter any website URL below. We analyze the HTML that builds the accessibility tree, score how readable it is to AI agents, and generate a custom fix prompt you can paste into any AI coding assistant.
Google documents three modalities that agents use to perceive a web page. Understanding all three helps you fix the right layer.
Vision models render the page as an image. This is slow and token expensive, so agents use it as a fallback when the structured layers are not available or are ambiguous.
The DOM structure and element relationships. Agents read it to understand the page, but it is verbose and includes layout and styling noise that is not relevant to interaction.
The semantic summary: roles, names, and states of interactive elements. Originally built for screen readers, it is now the map agents lean on for reliability and speed. It strips away everything that is not semantic.
You do not need a tool to see the accessibility tree. Chrome DevTools shows it directly.
Chrome DevTools, no extensions required
Right click any page and choose Inspect.
In the Elements panel, open the Accessibility tab. If you do not see it, click the double arrow to reveal hidden tabs.
Check "Enable full-page accessibility tree" and reload DevTools when prompted.
Click the accessibility icon that appears at the top right of the Elements tree. You are now reading your page the way an agent does: every node is a role and a name. If you see unnamed images, generic links, or buttons with no label, so does the agent.
The audit scores 100 points across six categories. Each category starts at full points and deducts per issue found, with a floor of zero per category.
30 points
Links with no accessible name, buttons with no label, form inputs with no associated label, and images missing the alt attribute entirely. Agents cannot operate or describe elements without names.
20 points
onclick handlers on div, span, li, or img without both a role and tabindex, elements with an interactive role but no tabindex, and anchors without href. Agents expect native interactive elements.
20 points
Missing or duplicate main landmark, missing nav, missing or duplicate h1, skipped heading levels, missing html lang attribute, and empty or missing title. Structure tells agents what each region is.
10 points
Generic anchor text like click here or read more, raw URLs as anchor text, and identical anchor text pointing to different destinations. Agents navigate by link text.
10 points
Body text content under a minimum threshold with a single empty framework root div, and missing meta description. Agents that do not run JavaScript see a blank page.
10 points
aria-hidden on containers with interactive elements, redundant roles on native elements, positive tabindex values, and aria-labelledby or label[for] referencing ids that do not exist.
The audit analyzes the HTML that builds the tree. Some issues only appear in the rendered tree, so use the Chrome steps above to verify the live result. A clean static structure is the foundation either way.
AI agents are already browsing on behalf of your customers. The accessibility tree is how they read your site, and most sites are hard to read.
Google's official guidance names the accessibility tree as one of three primary ways agents view a site, and its closing recommendations are to audit your accessibility tree and to read about WebMCP.
web.devWebAIM's survey of the top one million home pages finds empty links on nearly half of them and empty buttons on almost a third. Those are dead ends for an agent.
webaim.orgA 2026 study from UC Berkeley and the University of Michigan found agent task success fell from 78 percent to 42 percent when the accessibility tree was degraded.
searchenginejournal.comThe accessibility tree is how agents read and navigate your site. This audit measures it.
WebMCP is how your site hands agents structured tools to act with. The WebMCP audit measures it.
The accessibility tree is how agents read and navigate your site. WebMCP is how your site hands agents structured tools to act with. Google recommends both. Most of the web has neither. Fixing the read layer makes every agent visit work today. Adding the act layer makes your site a first class citizen when WebMCP capable browsers roll out. Run both audits and you have the full picture.
The same endpoint powers the on-page audit tool, the WebMCP-registered tool, and external API calls. Open to all, no auth required.
POST /api/audits/readability
url required The website URL to audit (e.g., "https://example.com")source optional Where the request originates: "api", "website", or "webmcp". Defaults to "api".urlNormalized URL that was audited
readability_score0 to 100 readability score
gradeLetter grade: A, B, C, D, or F
webmcp_detectedWhether navigator.modelContext was found
findingsPoints and issues per category, keyed by category name
recommendationsRanked next steps ordered by impact
fix_promptComplete prompt to paste into an AI coding assistant
checked_atISO timestamp of the audit
cURL
curl -X POST \
https://www.adaptmarketing.com/api/audits/readability \
-H "Content-Type: application/json" \
-d '{"url": "https://example.com", "source": "api"}'JavaScript
const response = await fetch(
'https://www.adaptmarketing.com/api/audits/readability',
{
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
url: 'https://example.com',
source: 'api'
})
}
);
const audit = await response.json();
console.log(audit.grade); // "B"
console.log(audit.readability_score);
console.log(audit.fix_prompt);Response
{
"url": "https://example.com",
"readability_score": 87,
"grade": "B",
"webmcp_detected": false,
"findings": {
"names_and_labels": {
"points_earned": 30,
"points_possible": 30,
"issues": []
},
"semantic_interactivity": {
"points_earned": 20,
"points_possible": 20,
"issues": []
},
"landmarks_and_structure": {
"points_earned": 13,
"points_possible": 20,
"issues": [
{
"check_id": "missing_main",
"explanation": "No main landmark found.",
"count": 1,
"severity": "high",
"examples": [{"snippet": "<body>", "note": "No main landmark."}]
}
]
},
"link_text_quality": { "points_earned": 9, "points_possible": 10, "issues": [] },
"rendered_content_signal": { "points_earned": 5, "points_possible": 10, "issues": [] },
"aria_hygiene": { "points_earned": 10, "points_possible": 10, "issues": [] }
},
"recommendations": ["No main landmark found (1 found)"],
"fix_prompt": "You are an accessibility...",
"checked_at": "2026-07-27T12:00:00.000Z"
}Rate Limiting
Maximum 10 audits per IP address per hour.
Results for the same URL are cached for 24 hours and returned instantly.
Rate-limited requests receive HTTP 429 with a retry_after_seconds field.
No. It checks the subset of accessibility signals that AI agents depend on to read and operate a page: names, roles, structure, and link clarity. Fixing them also helps screen reader users, but this is not a legal compliance review.
A simplified model of your page the browser builds automatically from your HTML. It lists every element with a role, a name, and a state. Screen readers have used it for two decades. AI agents now read it too.
Agent browsers render pages, but many AI crawlers do not. If your content only exists after JavaScript runs, part of your audience sees a blank page. Server rendered content is the safe baseline.
The WebMCP audit measures whether your site is ready to expose callable tools to agents. This audit measures whether agents can read and navigate the site you already have. Read layer and act layer. Run both.
Yes. Divs styled as buttons, icon buttons with no label, images with no alt text, and headings that are just bold text all look fine on screen and read as noise in the tree.
Copy the generated fix prompt into Claude, Cursor, or any AI coding assistant and it will walk through the exact issues found on your page. Or have us do it: we fix the read layer and the act layer together.
The audit tells you what agents cannot read. For a full implementation, semantic rebuild of key templates, labeling pass, landmark structure, and verification against the rendered tree, Adapt Marketing can help. Complete source code, documentation, and training. No recurring fees.