Server has 6 tools with clear verb-noun naming (get*, create*) and documented schemas. Descriptions are present but generic (avg ~80 chars, below 194-char baseline). Parameter descriptions exist but lack detail on constraints, formats, and dependencies. Output schemas are structured but not explicitly documented in tool definitions. Error handling is minimal, no recovery guidance or actionable error messages. Missing tool annotations (readOnlyHint/destructiveHint). One critical tool (createAlpacaOrder) lacks proper validation messaging.

• Expand tool descriptions to 100 - 200 chars. Example: 'getAlpacaAccountInformation: Retrieve your Alpaca account summary including portfolio value, cash balance, and trading status. Use this to check account health before placing orders.' This guides LLM selection and explains downstream use.
• Add tool annotations via fastmcp. Mark read-only tools with readOnlyHint=true; mark createAlpacaOrder with destructiveHint=true. This enables agents to reason about side effects.
• Document parameter constraints in descriptions. E.g., 'limit: Maximum number of orders to return (1 - 100, default 50)' and 'order_id: UUID string identifying the order (e.g., 550e8400-e29b-41d4-a716-446655440000)'.
• Enhance error messages in createAlpacaOrder. Replace ValueError with structured error: {'error': 'invalid_order_params', 'message': 'Specify either qty (shares) or notional (dollars), not both or neither.', 'recovery': 'Retry with one parameter set.'}
• Document output schemas in tool definitions. Add a 'returns' field or docstring snippet showing the response structure (e.g., 'Returns AlpacaOrder with fields: order_id, symbol, side, status, qty, notional, created_at, filled_at').

Inferred effective spec: 2025-06-18+.

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