Agent Readiness Check
agent-ready.dev
Checked 2026-09-08 06:04 UTC
Agents can partly use this site
An agent can read this site and get some way through it, with friction. The points still on the table are listed below, largest first.
Three fixes worth doing first
Ordered by the points still on the table. Each one comes from a documented check and, where it exists, with the code that fixes it.
01Honest annotations on tools
+5 ptsTools are registered without annotations, so an agent cannot tell reads from writes.
How to fix it Set readOnlyHint on every tool that only reads. Set untrustedContentHint where a tool returns text written by other users. Put a confirmation step in front of anything that spends money or changes state.
02Declarative tools on forms
+4 pts1 form(s) could be exposed as tools but none is annotated.
How to fix it Annotate the forms you already ship. Because the attribute names are still marked TODO in the explainer, verify them against the current specification before rolling this out widely.
03Forms an agent can fill
+3.5 ptsFields are partly described — an agent will guess at the rest.
How to fix it Give every field a <label for>, a meaningful name, the right input type, and an autocomplete token from the HTML standard.
<label for="email">Work email</label>
<input id="email" name="email" type="email"
autocomplete="email" required
aria-describedby="email-hint">
<p id="email-hint">We reply within one business day.</p>Your first WebMCP tool, matched to this page
The crawl found a a shop on this site, so the example below registers that as a tool an agent can call. Paste it, point it at your own endpoint, and the page stops being guessed at and starts being called.
registerTool
// Register the first tool an agent can call on this page.
// Works today with the polyfill: npm install @mcp-b/global
await document.modelContext.registerTool({
name: "search_products",
description: "Search the product catalogue by free text. Returns name, price and a link per match.",
inputSchema: {
type: "object",
properties: { query: { type: "string", description: "Free-text search term" } },
required: ["query"],
},
annotations: { readOnlyHint: true },
execute: async ({ query }, { signal }) => {
const res = await fetch(`/api/products?q=${encodeURIComponent(query)}`, { signal });
return { content: [{ type: "text", text: JSON.stringify(await res.json()) }] };
},
});.well-known/webmcp
{
"name": "agent-ready.dev",
"description": "Return a short summary of this site and links to its main sections.",
"tools": [
{
"name": "search_products",
"description": "Search the product catalogue by free text. Returns name, price and a link per match."
}
],
"pages": [
"https://agent-ready.dev/"
]
}The manifest at /.well-known/webmcp is the convention ChatGPT Desktop reads to list site tools. It is not part of the score yet; the registered tool above is.
llms.txt
# Agent Ready — AI Agent Readability Checker > Score any website against the Vercel Agent Readability Spec and llmstxt.org standard. Get actionable fixes to make your site AI-agent friendly. ## Main pages - [Start](https://agent-ready.dev/) - [About](https://agent-ready.dev/about) - [Contact](https://agent-ready.dev/contact)
Built from this page's own title and description. Replace the three links with your canonical pages.
Put the live badge on the site
The image is served from here and re-scores on its own. Every embed links back to this page.
<a href="https://webmcp-tool.com/check/agent-ready.dev" target="_blank" rel="noopener">
<img src="https://webmcp-tool.com/badge/agent-ready.dev.svg"
alt="Agent Readiness Score for agent-ready.dev: grade B, 85 out of 100 — measured by webmcp-tool.com"
width="208" height="40" loading="lazy" decoding="async">
</a>Agent Readiness Check
The full report, plus a re-check in 30 days
Every check with the evidence it was judged on and the code that fixes it, sent as a link that always re-scans. In 30 days we scan again and tell you what moved.
- All checks, pass by pass, with the exact header, count or path behind each verdict
- Copy-paste fixes generated from your own markup
- A re-check in 30 days with the difference, confirmed by you with one click
One email with the report, one re-check after you confirm it, and nothing else unless you ask. No account. Five reports per company per day. What we do with the address.
Agent Tracking
You know whether agents can read this site. Want to know what they do with it?
One line of script records which assistants send visitors, which pages they fetch, which WebMCP tools they call and whether they finish. No cookies, no personal data, hosted in Germany. The check score shows up in the dashboard and is re-scanned monthly.
<script defer data-domain="agent-ready.dev" src="https://webmcp-tool.com/agent.js"></script>
Compare with another site
A competitor, a client, the site you are about to ship. Two checks side by side, on one shareable address.
Open the full reportSee the best-scoring sites
Reports re-scan at most once an hour. Change something and open this address again.
Check another site
One request, about 20 seconds. No sign-up, no email. The result gets a shareable address.