Task Adherence evaluator doesn't show variables for ground_truth and tool_calls

[therealjohn]

This doesn't show all of the variables expected in the dataset. For example, the sample dataset is:

[microsoft-github-policy-service]

Thank you for contacting us! Any issue or feedback from you is quite important to us. We will do our best to fully respond to your issue as soon as possible. Sometimes additional investigations may be needed, we will usually get back to you within 2 days by adding comments to this issue. Please stay tuned.

[qinezh]

The sample dataset is fixed and always includes ground_truth, regardless of which evaluators are selected.

Task Adherence evaluator doesn't require ground_truth and tool_calls: https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/develop/agent-evaluate-sdk#-evaluate-other-agents