Server has 6 tools with complete input schemas and descriptions. Naming follows verb_noun convention (get_*, calc_*, compare_*). Descriptions are present but brief (10-80 chars), below the 50-200 char LLM-optimized baseline. All parameters have type definitions and descriptions. Output schemas are not documented, LLMs cannot predict response structure. Error handling returns structured ErrorResult JSON with code/message/details, which is good, but lacks recovery guidance (e.g., 'try search_users first'). No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All tools are READ_ONLY, which is safe but unmarked in the schema.

• Document output schemas for all tools. E.g., 'Returns: {symbol: string, price: number, change_percent: number, volume: integer}'. This enables LLMs to plan downstream operations.
• Expand tool descriptions to 50-200 chars. Add WHEN to use each tool. E.g., 'get_history: Fetch OHLCV data for technical analysis or backtesting. Use this before calc_indicators to ensure data freshness.'
• Add readOnlyHint: true to all tool schemas in list_tools(). Update types.Tool instantiation to include annotations parameter.
• Enhance error messages with recovery guidance. E.g., catch yfinance.TickerError and return 'Invalid symbol: XXXX. Valid symbols are uppercase (e.g., AAPL, MSFT). Try get_quote("AAPL") to verify.'
• Add offset/cursor pagination to get_news. Accept optional 'offset' parameter and return 'total_count' and 'has_more' fields so agents can iterate through large result sets.

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

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