Server has 12 tools with complete input schemas and descriptions. Naming follows verb_noun convention (search_, list_, get_, send_, download_). Descriptions are present (avg ~100 chars) but lack actionable context for LLM selection. Parameters are typed but many lack format constraints or validation guidance. Output schemas are not documented. Error handling is minimal, no recovery guidance or categorization. Security concern: send_message and send_file are destructive operations with no confirmation pattern. Missing pagination metadata (total_count, next_cursor) in list tools despite accepting limit/page params.

• Add output schema documentation for all tools. Example: list_messages returns {messages: [{id, sender, content, timestamp, media_type}], total_count, next_cursor}. This enables LLMs to chain tools correctly.
• Implement confirmation pattern for send_message, send_file, send_audio_message. Add a dry_run parameter or require explicit confirmation before executing irreversible operations.
• Document JID and phone number formats in parameter descriptions. Example: 'chat_jid: WhatsApp chat identifier (format: "[email protected]" for direct chats or "[email protected]" for groups)'.
• Add error recovery guidance. Example: 'If contact not found, call search_contacts() with a partial name. If send fails with 'not connected', verify WhatsApp session is active.'
• Return pagination metadata (total_count, next_cursor) in list_messages, list_chats, get_contact_chats responses so LLMs know when to fetch more results.