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

3433

Output Tokens

671

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 examined the provided tool list and identified that the 'database' tool offers a 'list_orders' method, which matches the requirement to retrieve orders for a specific customer. According to its schema, the 'list_orders' action requires two fields: 'action' set to "list_orders" and the 'customer_id' of the customer. Therefore, the correct tool/method pair is database → list_orders, with the corresponding parameter object.

Response: Use the 'database' tool with method 'list_orders' and send the parameters: {"action":"list_orders","customer_id":"cust_42"}