Guides
The work that pays off with every agent, not just WebMCP
Six things that decide whether an agent can read, understand and operate a site. Each one maps to a check in the score, and each one helps with the agents that have never heard of the standard.
robots.txt for AI agents
Which tokens matter, why the catch-all group is not a decision, and the longest-match rule that decides whether your own discovery endpoint is reachable.
5 sources · reviewed 27 August 2026
Content that survives without JavaScript
The most common and most expensive failure on the agentic web. Why an empty shell defeats the crawlers behind AI answers, how to tell whether you have one, and what to do when a rewrite is not on the table.
4 sources · reviewed 27 August 2026
Forms an agent can actually fill
The cheapest large improvement most sites can make. Labels, names, types and autocomplete tokens turn a guess into a certainty — and they are the same work the declarative WebMCP API will ask for.
4 sources · reviewed 27 August 2026
Structured data: the one place you state facts
Prose implies. JSON-LD asserts. Which types earn their keep for agent readiness, why validity matters more than volume, and the failure mode where markup and page disagree.
5 sources · reviewed 27 August 2026
llms.txt: what it is, and what it is not
A convention, not a standard, and ignored by Google Search. It is still worth publishing — because it is the one place you get to write the summary rather than hope one is inferred.
3 sources · reviewed 27 August 2026
Discovery documents, and the robots.txt trap
WebMCP tools only exist while a page is open. A discovery document is how an agent learns you exist before it arrives — and the most common failure is a site hiding its own manifest.
6 sources · reviewed 27 August 2026