Fetch a URL and return its main readable content as clean markdown by default (Readability extraction). Options: format=markdown|text|html|readable, includeLinks=false to strip hyperlinks, maxChars to truncate. Useful for reading a web page, understanding a code/docs page, or getting article content without boilerplate.

Extract all hyperlinks from a URL (or raw HTML). Returns array of {href, text, title, section, isExternal, hash, type} grouped to dedupe. Great for discovering pages/anchors before fetching them.

Search the content of a URL (or raw HTML) and return matching snippet(s) with surrounding context and line numbers. Useful to find specific text/code/errors on a page without reading the whole thing.

One-shot combo: fetch a URL and simultaneously return BOTH the cleaned content AND its links AND any matching search snippets. Most efficient when you want to understand a page and also navigate/search it. Omit pattern/links as needed.

Fetch an image from a URL (absolute or relative to a base page) and return it as base64 image content that the model can see. Use when a page's markdown contains relative image URLs (e.g. ) and you need to view the image. Optional compression can shrink oversized images to fit within maxSizeKB.