Fetch and extract structured content from a public URL. Useful for: reading articles, summarizing web pages, extracting facts from a source, understanding what a URL contains. Returns: title, summary, key_points[], extracted_facts[] (stated facts only, inference kept separate), source_url. Input: { url: string } — a public http/https URL (private network addresses are blocked). Output MIME type: application/json. Payment: x402 exact USDC on Base mainnet (eip155:8453).