All 11 tools have proper verb-noun naming (get_*) and structured input schemas with enums and type definitions. However, descriptions are in Chinese and extremely brief (10-20 chars), falling well below the 50-200 char LLM-optimized baseline. Parameter descriptions exist but are minimal. No output schemas are documented. Error handling and recovery guidance are absent. Tools are read-only (low risk) but lack the depth needed for confident LLM selection and multi-step planning.

• Translate all tool descriptions and parameter descriptions to English. Expand descriptions to 50-200 chars, explaining WHAT the tool does, WHEN to use it (e.g., 'Use this to track ARK fund buying/selling activity over time'), and any prerequisites (e.g., 'Requires valid stock code in MARKET.SYMBOL format').
• Document output schemas for all 11 tools. For each, specify: field names, types (string, number, array, object), and what each field represents. Example: 'Returns array of {symbol: string, shares_change: number, market_value: number, weight_percent: number}'.
• Add error handling with recovery guidance. For 'stock code not found' errors, return available markets and example codes. For API timeouts, indicate retry is safe. For permission errors, explain what credentials are needed.
• Expand parameter descriptions to include format constraints and valid ranges. E.g., 'cycle: Time period for aggregation. ONE_DAY = last 1 trading day, FIVE_DAY = last 5 trading days, etc. Defaults to ONE_DAY if omitted.'
• Add a discovery tool or documentation endpoint that lists supported stock codes, markets, and available data ranges. This prevents agents from guessing invalid codes and reduces failed calls.