ai-agents-tool-input-parsing-llm-outputs-json-string-tool-input-but-it-is-not-p-a5ebc321

THEN Ensure tool input parsing handles JSON strings robustly, especially for boolean and None values. One workaround is to instruct the LLM to output JSON strings with string representations of booleans and None (e.g., 'True' → '"True"') or to implement a pre-processing step that converts JSON strings into dictionaries before passing to the tool. Alternatively, adjust the tool's args_schema to accept a JSON string directly and parse it internally.

def _run(self, argument: str) -> Dict:
    try:
        params = json.loads(argument)
        # Ensure booleans/None are handled
        params = {k: str(v) if isinstance(v, (bool, type(None))) else v for k, v in params.items()}
        return ResearchTool.arxiv_research_tool(argument)
    except Exception as e:
        return {"error": str(e)}