Single tool with adequate naming but significant gaps in description and schema documentation. The tool 'get_current_temperature' follows verb_noun convention, but the description is minimal (35 chars, below the rubric baseline of 194 chars average). Input schema is present but lacks type descriptions for parameters. No output schema is documented. The server appears to be a bridge/proxy rather than the primary tool source, the actual tool is defined in mock-weather-mcp-server/main.py using FastMCP, but registration details for the bridge itself are not visible in provided source. This limits confidence in tool composition and error handling quality.

• Expand tool description to 100-200 chars: 'Retrieve the current temperature in a specified city in Celsius. Use this when the user asks about weather conditions or temperature for planning purposes.' This provides LLM selection context.
• Add parameter description in schema: change the 'city' property object to include 'description': 'The name of the city (e.g., New York, London, Tokyo). Free-form string, searches for matching cities.'
• Document the response schema: specify that the return is a string in format 'The current temperature in {city} is {temp}°C.' so LLMs know how to parse the response.
• Add error handling guidance: 'If the city is not found or the weather service is unavailable, the tool will return an error message. Suggest the user clarify the city name or try a major city.'
• Make tool registration explicit in the bridge server code (src/ollama_mcp_bridge/api.py or similar) so tool definitions are visible for inspection and validation.

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

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