Five tools with complete input schemas and descriptions, but descriptions are generic and lack LLM-optimized guidance. All tools are READ_ONLY (good for safety), but descriptions don't explain WHEN to use each tool vs. alternatives, or what downstream actions become possible. Parameter descriptions are present but minimal. No output schemas documented. Error handling and recovery guidance absent. Naming is clear (verb_noun pattern) but descriptions average ~100 chars, below the 50-200 char LLM-optimized baseline.

• Document output schemas for all five tools. E.g., mpp_inspect should return {challenge: {fields...}, verification: {status, details}, timing: {ms}}. This enables LLMs to chain tools and extract IDs.
• Expand descriptions to 100-200 chars with WHEN/WHY guidance. E.g., 'Use mpp_inspect to parse a single 402 challenge and verify its signature. Use mpp_flow for a full dry-run of the payment flow.'
• Add error handling guidance to each tool description. E.g., 'Returns error if URL is unreachable (timeout after 30s), malformed (invalid JSON in challenge), or signature verification fails. Suggest retrying with different URL or checking network.'
• Enhance parameter descriptions with format and constraint details. E.g., headers: 'Array of HTTP header strings in format "Key: Value". E.g., ["Authorization: Bearer token", "X-Custom: value"]. Max 10 headers.'
• Add a 'prerequisites' or 'related_tools' hint to descriptions. E.g., mpp_compare: 'Call mpp_scan first to discover MPP endpoints on a domain, then pass URLs to mpp_compare to find the cheapest option.'