Server has 14 tools with complete input schemas and descriptions. Naming follows verb_noun convention (send_message, read_messages, list_chats, etc.). Descriptions are present and adequate (avg ~100 chars), but lack LLM-optimized guidance on WHEN to use each tool vs. similar ones. Parameters are typed and mostly described, but lack constraints (enums, ranges, patterns). Output schemas are not documented, LLMs cannot predict response structure. Error handling is minimal; no recovery guidance. Missing tool annotations (readOnlyHint, destructiveHint) despite having tools with clear risk profiles (delete_message, leave_chat are DESTRUCTIVE/IRREVERSIBLE but unmarked).

• Document output schemas for all tools. Example: send_message returns {message_id: string, timestamp: integer, chat_id: integer}. Include all fields agents need for chaining (e.g., message_id for edit_message, chat_id for follow-up calls).
• Add tool annotations: mark delete_message and leave_chat with destructiveHint=true; mark send_message, edit_message, pin_message with idempotentHint=false (or true if idempotent). This enables agents to reason about retry safety.
• Enhance descriptions with WHEN-to-use guidance. Example: 'Read messages from a Max chat. Use this to fetch message history by chat_id, timestamp range, or specific message IDs. For real-time updates, use get_updates() instead.'
• Add parameter constraints to descriptions. Example: 'count: Number of messages to return (1-100, default 50). Larger values may timeout.' Document enum defaults: 'format: Text format (markdown, html, or plain text if omitted).'
• Improve error messages with recovery hints. When chat_id is invalid, return: 'Chat not found. Call list_chats() to see available chats, or verify the chat_id is numeric.' When message_id is invalid, suggest: 'Message not found. Call read_messages(chat_id=...) to fetch recent messages and find the correct message_id.'

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

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