This server has critical definition quality issues. Only 2 unique tools exist (earthquake_probability, next_volcanic_eruption), but the tool list duplicates them. Descriptions are present but minimal (10-40 chars, below the 50-200 char LLM-optimized baseline). earthquake_probability has a parameter schema with type and description, but next_volcanic_eruption accepts no parameters. No output schemas are documented. No error handling guidance. No tool annotations (readOnlyHint, destructiveHint, idempotentHint). The fastmcp.py implementation shows async functions but no explicit schema registration visible in the code, tool definitions appear inferred from decorators rather than explicitly registered with full schemas.

• Expand tool descriptions to 50-200 characters. Example: 'earthquake_probability: Estimate seismic risk for a location (0-1 scale). Use this to assess hazard before planning infrastructure or travel. Returns probability as a float.'
• Add explicit output schema documentation. For earthquake_probability, document: 'Returns: float (0.0 to 1.0, where 1.0 = certain earthquake)'. For next_volcanic_eruption, document: 'Returns: string (volcano name and location, e.g. "Mt. Vesuvius (Italy)").'
• Add parameter descriptions for earthquake_probability's 'location' param. Current description is bare. Expand to: 'location (string): Geographic location name or coordinates (e.g. "San Francisco", "37.7749,-122.4194"). Required.'
• Register tools with readOnlyHint=true in tool annotations to signal to LLMs that these are safe to call without confirmation.
• Add error handling guidance. E.g., 'If location is invalid or not found, returns 0.0 (no data). Consider calling a location validation tool first if needed.'

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

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