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

3737

Output Tokens

592

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: To list all orders for a specific customer, I need to use the 'database' tool, which is responsible for reading and updating order-management data. Within this tool, the 'list_orders' method is explicitly designed to retrieve a list of orders associated with a customer ID. According to the provided schema for 'list_orders', the required parameters are 'action' (set to 'list_orders') and 'customer_id' (which is 'cust_42' in this case).

Response: Tool: database; Parameter object: {"action": "list_orders", "customer_id": "cust_42"}