Server exposes 4 read-only tools via HTTP transport with basic schemas and descriptions. Tool names follow verb_noun convention (get_*, list_*, search_*). All tools have descriptions (34-56 chars, below the 50-200 char optimum). Input schemas are present but minimal: get_page_content has 1 param with type and description; search_site has 2 params with types and descriptions; get_sitemap and list_content have empty input objects. No output schemas documented. No error handling guidance. No parameter constraints (enums, ranges). Descriptions lack WHEN/WHY context and dependency hints. No tool annotations (readOnlyHint present in metadata but not in schema). Overall: functional but sparse, typical of community servers.

• Document output schemas for all tools. E.g., get_page_content returns {url, title, description, markdown, metadata}; search_site returns [{url, title, description, snippet, score}].
• Expand descriptions to 80-150 chars. Add WHEN/WHY context: 'List all content pages with metadata. Call this first to discover available pages before fetching individual content.'
• Add parameter constraints: search_site limit should be 1-100 (default 20). Document in description: 'Maximum number of results (1-100, default 20).'
• Add error handling guidance: 'If page not found, try search_site() to find similar pages by title or description.'
• Distinguish get_sitemap vs list_content in descriptions. E.g., 'get_sitemap: Returns URLs only (lightweight). list_content: Returns full metadata (title, description, type).'