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.

Duration

Input Tokens

3370

Output Tokens

388

Cost

$0.00

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: I need to identify the appropriate tool and parameters for listing all open orders for customer with ID 'cust_42'. After reviewing the available tools, I can see the 'database' tool has a 'list_orders' method that's designed for this purpose. According to the schema, this method requires two parameters: 'action' with value 'list_orders' and 'customer_id' with the specific customer ID. The customer ID provided in the task is 'cust_42', so I'll use that exact value.

Response: I choose the 'database' tool with the 'list_orders' method. The parameter object I would send is:

{
  "action": "list_orders",
  "customer_id": "cust_42"
}