Prusa MCP has 6 tools with consistent naming (verb_noun pattern: get_*, connect_*) and complete input schemas with type definitions. However, descriptions are minimal (10-50 chars), parameter descriptions lack detail about constraints/formats, and output schemas are entirely undocumented. No error handling guidance, no pagination support despite list tools, and no tool annotations. Naming is clear but descriptions fall well below the 50-200 char LLM-optimized baseline.

• Expand tool descriptions to 80-150 characters. Example: 'Get detailed status of a specific printer' → 'Retrieve real-time status of a Prusa printer including temperature, print progress, and connectivity state. Requires printer_uuid from get_printers().'
• Add parameter constraints to descriptions: 'limit: Maximum number of items to return (1-100, default: 10)' and 'printer_uuid: UUID string identifying the printer (obtain from get_printers)'.
• Document output schemas for each tool. Specify which fields are returned (e.g., get_printers returns [{ printer_uuid, name, status, ... }]) so LLMs can chain calls.
• Add pagination support to list tools: accept offset/limit or cursor parameters, return total_count and next_cursor in responses to enable iteration over large result sets.
• Declare tool annotations via @mcp.tool(readOnlyHint=True) for all read-only tools to enable client-side safety optimizations.

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

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