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

17s

Input Tokens

3370

Output Tokens

375

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 retrieve all open orders for customer ID "cust_42". Among the available tools, the one that can query orders is the "database" tool. Inspecting its params_schema shows that the action "list_orders" requires exactly two fields: "action" (constant "list_orders") and "customer_id" (the target customer). Therefore, the correct method is the database tool’s "list_orders", and the parameter object must include those two fields, with customer_id set to "cust_42".

Response: Tool: database (method "list_orders")
Parameter object:
{
  "action": "list_orders",
  "customer_id": "cust_42"
}