Four tools with basic schemas and minimal descriptions. All tools have input schemas with type definitions, but descriptions are generic (10-50 chars, well below the 194-char baseline). No parameter descriptions beyond the bare minimum. No output schemas documented. No error handling guidance. Tool names follow verb_noun convention (web_search, scrape_webpage, calculator, summarize_text) but lack specificity about when to use each vs alternatives. No pagination, no structured output guidance, no recovery hints.

• Expand all tool descriptions to 100-200 characters. Include WHAT the tool does, WHEN to use it (vs similar tools), and WHAT it returns. Example: 'web_search: Search the web for information. Returns up to 10 results with title, URL, and snippet. Use this to find relevant pages; then call scrape_webpage to extract full content.'
• Document output schemas for each tool. Specify return type (object, array, string), field names, and types. E.g., web_search returns [{title: string, url: string, snippet: string}]. This enables LLMs to chain tools correctly.
• Add parameter descriptions with constraints. E.g., 'query (string, 1-500 chars): Search terms. Supports AND, OR, NOT operators.' 'max_length (integer, 50-5000): Maximum summary length in characters.'
• Add error handling guidance to tool descriptions. E.g., 'If web_search returns no results, try broader keywords or use scrape_webpage directly if you have a URL. If rate-limited, wait 60 seconds before retrying.'
• Implement pagination for web_search results. Add optional 'page' (default 1) and 'limit' (default 10, max 50) parameters. Return total_results count so LLMs know when to fetch more pages.

Inferred effective spec: <=2025-11-25.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry