> ## Documentation Index
> Fetch the complete documentation index at: https://www.landbase.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Read Webpage

> Point at any URL and extract clean, structured content — company sites, job boards, landing pages.

<div id="breadcrumb-wrapper" />

<div
  style={{display: 'none'}}
  data-related-resources={JSON.stringify([
{ title: 'Search the Web', href: '/reference/tools/search-the-web' },
{ title: 'Qualify Leads', href: '/reference/tools/qualify-leads' },
{ title: 'Tools overview', href: '/reference/tools' }
])}
  id="page-related-resources"
/>

# Read Webpage

<div className="blog-post-content">
  Point the agent at any URL and get clean, structured text back. Company websites, job boards, landing pages, news articles, pricing pages — the system reads the page and returns the content as markdown.

  ## Automatic headless detection

  Modern websites use JavaScript frameworks (React, Vue, Angular) that show nothing to a basic HTTP request. Read Webpage detects this and automatically switches to a headless browser that renders the page like a real user would see it. You don't have to know or care which mode is needed.

  ## What it returns

  * **Clean markdown text** — extracted from the page content, not raw HTML
  * **Meta description and keywords**
  * **A numbered link map** — all links found on the page, indexed for easy reference

  ## When it's used

  Most often used by [Qualify Leads](/docs/reference/tools/qualify-leads) (to research company websites per record) and by the agent when you ask "what's on this company's pricing page?" It's a general-purpose tool — any URL, any content.
</div>