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: Let me analyze the task step by step:

1. The user wants to list all open orders for customer ID 'cust_42'
2. Looking at the available tools, I have access to a 'database' tool with multiple methods
3. Among the database methods, I can see 'list_orders' which seems most appropriate for this task
4. According to the schema for 'list_orders' action:
   - It requires 'action' field set to 'list_orders'
   - It requires 'customer_id' field with the customer ID
5. The parameter object should follow the schema structure defined for the database tool when action is 'list_orders'

Based on the instructions, I should use the database tool with the list_orders method, providing the customer_id as required by the schema.

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

**Tool:** database
**Method:** list_orders

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

This parameter object conforms to the database tool's schema for the 'list_orders' action, which requires both the 'action' field (set to 'list_orders') and the 'customer_id' field (set to 'cust_42'). This will retrieve all orders associated with that specific customer.