Three tools with complete schemas and reasonable descriptions. All tools follow verb_noun naming (hn_top_stories, hn_get_story, hn_search). Descriptions are 100-180 chars, within the 10-1024 baseline. Input parameters have types and descriptions. However, output schemas are not documented, LLMs cannot predict response structure. Error handling is present but generic ('HN API unavailable'). No parameter constraints beyond min/max on numeric fields. Missing enum validation for search query patterns.

• Document output schema for each tool. Example: 'Returns array of {title: string, author: string, score: number, url: string, id: number}'. LLMs need to know what fields to extract.
• Enhance error messages with recovery guidance. E.g., 'HN API timeout (retryable). Wait 5s and try again.' or 'Invalid query syntax. Try: search term without special chars.'
• Add enum or pattern constraint to hn_search 'query' parameter. Document valid operators (if any) and character restrictions.
• For hn_get_story, when rejecting non-story items, suggest hn_search as an alternative: 'Item is a comment. Use hn_search to find stories mentioning this topic.'
• Add pagination to hn_top_stories and hn_search: accept 'offset' parameter and return 'total_count' in response to enable multi-page retrieval.