The agent is passing placeholder text instead of actual data to the tool

How can I ensure my AI agent passes actual data to a tool instead of just a placeholder string?
Currently, the agent sends a generic text like "list of records" instead of the real data, which causes a validation error. Is there a way that the agent passes the actual data and structure to the tool?

Tool Output:

I encountered an error while trying to use the tool. This was the error: Arguments validation failed: 1 validation error for Analyze_Inventory_Tool
inventory_data
Input should be a valid list [type=list_type, input_value=‘list of inventory records’, input_type=str]
For further information visit Redirecting....
Tool analyze_inventory_tool accepts these inputs: Tool Name: analyze_inventory_tool
Tool Arguments: {‘inventory_data’: {‘description’: None, ‘type’: ‘list[dict]’}, ‘item_name’: {‘description’: None, ‘type’: ‘str’}}
Tool Description:
Analyze inventory levels for a specific item across fulfillment centers.

Args:
    inventory_data (List[Dict]): List of inventory records with fields:
        - Item_Name: Name of the item
        - Node_Name: Location/fulfillment center name
        - Available_Quantity: Number of items available
    item_name (str): Name of the item to analyze (case-insensitive)
    
Returns:
    Dict: {
        "success": bool,
        "message": str,
        "locations": List[Dict[str, Any]],
        "total_quantity": int
    }
.

Moving on then. I MUST either use a tool (use one at time) OR give my best final answer not both at the same time. When responding, I must use the following format:

Thought: you should always think about what to do
Action: the action to take, should be one of [analyze_inventory_tool]
Action Input: the input to the action, dictionary enclosed in curly braces
Observation: the result of the action

This Thought/Action/Action Input/Result can repeat N times. Once I know the final answer, I must return the following format:

Thought: I now can give a great answer
Final Answer: Your final answer must be the great and the most complete as possible, it must be outcome described