ai-agents-tool-schema-mismatch-pydantic-validationerror-when-llm-returns-a-dict-i-a89c193a

THEN Define all tool parameters with explicit type hints (e.g., `category: str`). If the model may still return dicts, add a parsing guard in the tool function to extract the expected value or convert to string.

@tool
def GetNewQuestion(category: str) -> str:
    if isinstance(category, dict):
        category = category.get('category', 'general')
    return f'What is your experience with {category}?'