Single tool 'check_mapdl_status' has critical definition gaps. Input schema is empty object {} with no parameters documented. Description is present (194 chars) but generic and lacks actionable guidance on when/why to call it. No output schema visible in source. Tool name lacks action verb clarity ('check' is weak; 'get_mapdl_status' or 'verify_mapdl_initialization' would be stronger). No parameter descriptions, no error handling guidance, no recovery paths. Tool appears read-only but lacks explicit idempotentHint annotation. Source code inspection shows tool registered in tools.py but actual implementation details not provided in sample, preventing full schema validation.

• Rename tool to 'get_mapdl_status' or 'verify_mapdl_initialization' to use a clear action verb that signals intent to the LLM.
• Document the complete output schema with all fields, types, and descriptions. Example: {status: 'initialized'|'exited'|'exiting', version: string, uptime_seconds: number, ...}
• Expand description to 100-150 chars explaining: (1) What it does: 'Retrieves the current state of the MAPDL instance'; (2) When to use it: 'Call this before running simulations to verify MAPDL is ready'; (3) What it returns: 'Status, version, and initialization details'.
• Add explicit error handling: document what happens if MAPDL is not running, has crashed, or is in an invalid state. Provide recovery guidance (e.g., 'If status is exited, call initialize_mapdl() first').
• Add tool annotation 'readOnlyHint: true' to signal this is a safe, non-destructive read operation that can be retried without side effects.

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

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