Opper

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.

Input Tokens

Output Tokens

Duration

Cost

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: <think>
The task is to list all open orders for a specific customer whose ID is `cust_42`. 
From the context, we have access to several tools, but the relevant one here is the `database` tool. 
The `database` tool has a method called `list_orders` which seems suitable for this task. 
The `list_orders` method requires a parameter object with the following structure: 
```json
{
  "action": "list_orders",
  "customer_id": "string"
}
```
Given the customer ID is `cust_42`, we can construct the parameter object accordingly. 
Therefore, the tool/method to choose is `database.list_orders` and the parameter object to send is:
```json
{
  "action": "list_orders",
  "customer_id": "cust_42"
}
```
</think>

**Summary of Approach:**
1. Identify the relevant tool and method for the task: `database.list_orders`.
2. Construct the parameter object with the required fields (`action` and `customer_id`).
3. Use the provided customer ID `cust_42` in the parameter object.

Final Answer:
database.list_orders with parameter object {"action": "list_orders", "customer_id": "cust_42"}

Response: database.list_orders with parameter object {"action": "list_orders", "customer_id": "cust_42"}