You add a plugin tool to a Copilot Studio agent that can retrieve customer account balances. Despite being configured correctly, the generative orchestrator rarely invokes the tool when users ask about their balance. What is the most likely configuration issue?
Select an answer to reveal the explanation.
Short Explanation and Infographic
The AI orchestrator reads tool descriptions like a job posting — if it can't tell from the description that 'retrieve account balance' is what this tool does, it won't know to call it when balance questions come up. A rich, specific description is the orchestrator's signal to act.
Full explanation below image
Full Explanation
When Copilot Studio's generative orchestrator decides which tools, topics, or child agents to invoke for a user's request, it uses the natural language description of each registered tool to determine relevance. If a tool's description is vague (e.g., 'retrieves information') rather than specific (e.g., 'Retrieves the current account balance, available credit, and last payment date for a customer account given the customer ID'), the AI cannot match it to user queries about balances.
The fix: write a detailed, specific tool description that names the exact use cases, the data it returns, and the inputs it needs. This is called 'tool prompt engineering' and is critical for reliable generative orchestration.
Option A (missing API key) — if the API key were missing, the tool would fail when called (returning an error), not fail to be selected. The symptom here is non-invocation, not invocation failure.
Option C (tools only callable from topics, not orchestrator) — this is incorrect. Tools can be discovered and invoked by the generative orchestrator directly when their descriptions match user intent.
Option D (user must say tool name) — generative orchestration is intent-based, not name-based. Users should never need to know tool names.
Critical exam rule: poor tool description → orchestrator does not invoke the tool. Invest time in clear, specific tool descriptions. This is analogous to writing good system prompt tool descriptions for function calling in LLM APIs.