Single tool with minimal definition quality. Tool name 'scrape_markdown' is action-verb-based (positive), but description is extremely brief (54 chars, below 10-char minimum for context). Input schema present but lacks parameter descriptions, the 'url' parameter has only a generic description. No output schema documented. No error handling guidance. No parameter constraints (format, length, allowed values). Tool definition appears inferred from verify_mcp.py rather than explicit server registration code.

• Expand description to 100 - 200 chars: 'Fetch and convert a URL to markdown. Useful for extracting article text, documentation, or web content. Returns markdown-formatted text. Supports HTTP/HTTPS URLs only. Fails on invalid URLs, timeouts (>30s), or non-text content.'
• Add parameter description for 'url': 'The HTTP or HTTPS URL to scrape (e.g. https://example.com). Must be a valid, publicly accessible URL. Relative URLs not supported.'
• Document output schema: 'Returns an object with fields: { content: string (markdown-formatted text), url: string (the requested URL), status: number (HTTP status), error?: string (if scraping failed) }'
• Add error handling examples: 'If URL is invalid, returns error with message. If timeout occurs, retry with a shorter URL or check network. If content is binary, returns error suggesting a different tool.'
• Add parameter constraints: url must match regex ^https?:// and be <2048 chars. Validate early and return actionable error messages.