Model Context Protocol for summarizing Hacker News discussions
Single tool with adequate naming and schema, but significant gaps in parameter descriptions and output documentation. Tool name 'get_hn_post_formatted_comments' follows verb_noun convention and clearly conveys action. Input schema is present with type definitions. However, the post_url parameter description lacks format constraints (accepts both URL and numeric ID but doesn't specify the format clearly). Output schema is declared but lacks detailed field descriptions, 'content' and 'metadata' are vaguely documented. No error handling guidance provided to LLMs. Tool description is 194 chars (within baseline 34-392 range) but could better explain when to use this tool vs alternatives or what 'formatted' means. Missing: parameter validation rules, output field type details, error recovery guidance.
Retrieves and formats comments from a Hacker News discussion post for summarization by an LLM. Use the `hacker_news_summarization_user_prompt` prompts to generate a summary.
Output schema lacks detailed field descriptions. 'content' is documented as 'array' but doesn't specify element types or structure. 'metadata' object properties (postId, commentCount, postUrl) are not individually described.
Parameter 'post_url' description mentions both URL and numeric ID formats but lacks explicit format constraints. Should state: 'Either a full URL (https://news.ycombinator.com/item?id=XXXXX) or numeric post ID (e.g., 43456723)' with regex pattern or enum-like guidance.
No error handling guidance. Tool throws generic errors ('Invalid post URL', 'Failed to download comment post') without recovery hints. LLM cannot determine if error is retryable, user-fixable, or fatal.
Inferred effective spec: 2025-06-18+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 53 | 2025-06-18+ | v2 |
Output content array mixes two unrelated items (formattedComments and userPrompt) with only 'description' field to distinguish them. Should use typed objects with explicit 'type' field or separate response fields for clarity.
Tool description does not explain when to use this tool or what 'formatted' means. Should clarify: 'Fetches and formats Hacker News comments into a structured text format suitable for LLM summarization. Use this before calling an LLM summarization tool.'