Opper

Agents

AI agent reasoning and tool selection tests planning, tool choice, and self-diagnosis capabilities. These skills are crucial for autonomous ticket triage systems and complex agent workflows where models must decide which tools to use, plan multi-step processes, and diagnose when things go wrong. This represents some of the most challenging tasks as they require open-ended reasoning and decision-making.

Input Tokens

Output Tokens

Duration

Cost

Context

Input

You need to list all open orders for a specific customer whose ID is `cust_42`. Which tool/method do you choose and what parameter object do you send?

Expected output

Use the **database** tool with parameters {"action": "list_orders", "customer_id": "cust_42"}.

Model output

Reasoning: To list all open orders for customer ID 'cust_42', I need to:
1. Identify the appropriate tool from the available tools
2. Select the correct method/action for listing orders
3. Construct the proper parameter object with the required fields

From the context, I can see the 'database' tool has a 'list_orders' method that takes a customer_id parameter. This is exactly what I need to retrieve all orders for a specific customer.

According to the schema for the database tool:
- The action must be 'list_orders'
- It requires 'customer_id' as a parameter
- The customer_id should be 'cust_42' as specified in the task

Response: To list all open orders for customer ID 'cust_42', I would use:

**Tool:** database

**Parameter object:**
```json
{
  "action": "list_orders",
  "customer_id": "cust_42"
}
```

This will retrieve all orders associated with customer 'cust_42'. The database tool's 'list_orders' method is specifically designed for this purpose and requires only the customer_id to fetch all orders for that customer.