Swiss Energy MCP demonstrates solid tool design with consistent naming patterns (all tools start with 'energy_'), complete input schemas with proper types and descriptions, and clear parameter documentation. All 10 tools follow verb_noun convention and include WGS84 coordinate guidance. However, tool descriptions are brief (avg ~80 chars, below the 194-char baseline), lack WHEN-to-use context, and output schemas are not explicitly documented in the visible code. Error handling and recovery guidance are absent. The server shows good fundamentals but lacks the depth expected for A-grade production tools.

• Expand tool descriptions to 100-200 chars. Add WHEN-to-use guidance: 'Use this to find specific power plant types near a location. Call energy_location_profile instead if you need a comprehensive energy overview. Requires WGS84 coordinates (lat/lon).'
• Document output schemas explicitly in tool descriptions or in a separate schema reference. State: 'Returns EnergyResponse with fields: results (array of {name, type, capacity_mw, coordinates}), summary (markdown), source (string), license (string), match_type (exact|none).'
• Add error handling guidance to each tool description. E.g., 'If no results found, try expanding radius_m or checking energy_check_status to verify data source availability.'
• Add limit and offset/cursor parameters to search tools (energy_find_power_plants, energy_search_bfe_datasets) with documented defaults (e.g., limit=20, default offset=0). State max result cap in description.
• Declare tool annotations in the tool schema: add readOnlyHint=true to all 10 tools to signal to clients that these are safe, non-destructive operations per spec 2026-07-28.

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

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