13 tools with explicit schemas and descriptions. Naming is action-verb consistent (daemon_status, poll_events, acknowledge_event, etc.). Descriptions are present but brief (avg ~80 chars, below the 194-char baseline). Parameter descriptions exist but lack detail on constraints, formats, and error recovery. Output schemas are not documented, LLMs cannot predict response structure. Error handling is minimal; no recovery guidance. Composition is sound (single responsibility per tool), but missing idempotency hints and chaining IDs in responses.

• Document output schemas for all tools. Include field names, types, and nested structure. E.g., daemon_status returns {running: boolean, gateway: boolean, methods: number, message: string}. This enables LLMs to plan downstream calls.
• Expand descriptions to 100 - 200 chars. Add WHEN to use, prerequisites, and error recovery. E.g., 'Poll unacknowledged events from background automations. Call this after create_cron to check if the job ran. Returns up to 50 events; use offset for pagination. If no events, the automation may not have triggered yet.'
• Add constraint details to parameter descriptions. E.g., 'schedule: Cron expression (5 fields: minute hour day month weekday, e.g., "0 9 * * *" for 9am daily). Invalid syntax will be rejected.' Validate and return actionable errors.
• Add error recovery guidance. E.g., acknowledge_event: 'If event not found, call get_event_history() to verify the event ID. Events expire after 30 days.'
• Implement confirmation for destructive tools. Add a 'confirm' boolean parameter (default false) or a separate 'confirm_delete_automation' tool. Require explicit confirmation before deleting automations or pruning events.