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

3478

Output Tokens

193

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: The task is to list all open orders for customer ID `cust_42`. First, I analyze the available tools and their schemas. The `database` tool has a method `list_orders`, which — according to its schema — requires two parameters: `action` (set to `'list_orders'`) and `customer_id`. The context confirms this, as the `list_orders` action requires `customer_id`. Since the customer ID is provided (`cust_42`), I can directly construct the parameter object to invoke `list_orders` via the database tool. No prior tool calls are needed because I already have the required customer ID and can directly form the request.

Response: I will use the `database` tool with the `list_orders` action. The parameter object to send is: {"action": "list_orders", "customer_id": "cust_42"}.