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

281

Cost

$0.03

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 orders from the order-management database. The available database tool includes a `list_orders` method, and its schema requires `action` and `customer_id`. There is no explicit `status` or `open_only` parameter in the schema, so the correct parameter object should only include the supported fields. Any filtering for open orders would need to be handled from the returned order list if the tool returns mixed statuses.

Response: Use the `database` tool with the `list_orders` method.

Parameter object:
```json
{
  "action": "list_orders",
  "customer_id": "cust_42"
}
```