19 tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. Most tools have 1-3 parameters with minimal descriptions (10-30 chars). No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Output schemas are not documented, LLMs cannot predict response structure for chaining. Error handling is absent; no recovery guidance. Naming is verb-first (good), but descriptions lack WHEN/WHY context. Credential tools expose sensitive operations without confirmation patterns. No pagination guidance despite list tools. Baseline: 549 production tools average 194 chars per description; these average ~60 chars.

• Add output schemas to all tools. Document response fields, types, and pagination. E.g., n8n_list_workflows should declare: {workflows: [{id, name, active, ...}], total: int, limit: int}.
• Add tool annotations: mark n8n_delete_* as destructiveHint=true, n8n_get_* as readOnlyHint=true, n8n_activate_workflow as idempotentHint=true. Spec 2026-07-28 requires these for risk classification.
• Expand parameter descriptions to 50-150 chars. Include format hints, valid ranges, and dependencies. E.g., 'workflowId: The n8n workflow UUID (36 chars, from n8n_list_workflows). Required.'
• Add error recovery guidance to tool descriptions. E.g., 'If workflow not found (404), call n8n_list_workflows to verify the ID exists. Workflow must be deactivated before deletion.'
• Implement confirmation pattern for credential operations. Add a 'confirm' boolean parameter or require a separate confirm_credential_change tool to prevent accidental secret leaks.

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

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