Databricks-GenAI-Assoc Design Applications Practice Question
A GenAI engineer is designing an agentic application on Databricks that uses a foundation model to decide which external tools to call. The team wants the agent to be able to invoke a Databricks SQL warehouse query and a Python function registered as a Unity Catalog function, and they need the model to select tools based on natural language requests. Which design element is required for the model to select and invoke these tools correctly?
⚠ Common exam trap
The trap here is assuming that fine-tuning or logging replaces the runtime tool definitions, when the model needs explicit function schemas in every request to invoke tools correctly.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Provide tool definitions with names, descriptions, and parameter schemas to the model in the request.
Function-calling models rely on tool definitions passed in the request, including name, description, and parameter schema, to decide which tool to invoke and how to format arguments. Providing these definitions for the SQL warehouse query and Unity Catalog function gives the model the runtime contract it needs. Fine-tuning, volume storage, and inference tables do not supply that contract and therefore cannot enable correct tool selection.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Enable inference tables on the model serving endpoint to capture tool calls.
Why it's wrong here
Inference tables log requests and responses for monitoring and auditing, but they do not provide tools to the model. Enabling them does not give the model knowledge of tool names, descriptions, or parameter schemas, so the agent still cannot select or invoke tools. Inference tables are an observability feature, not a mechanism for tool registration or function calling.
- ✗
Store the tool list in a Unity Catalog volume and have the agent read it before each request.
Why it's wrong here
Unity Catalog volumes store files, not runtime context for a model. A model cannot read a volume during inference; the tool definitions must be included in the request payload. Storing them in a volume adds an unnecessary file-read step and still requires passing the definitions to the model. This design confuses data storage with the inference-time contract required for function calling.
- ✓
Provide tool definitions with names, descriptions, and parameter schemas to the model in the request.
Why this is correct
Function-calling capable models select tools based on the tool definitions supplied in the request, which include the tool name, a natural language description, and a JSON schema for parameters. Without these definitions, the model has no knowledge of available tools or how to structure arguments. Supplying accurate definitions for the SQL warehouse query and the Unity Catalog function enables correct tool selection and argument generation.
- ✗
Fine-tune the foundation model on the team's historical tool-call logs.
Why it's wrong here
Fine-tuning can improve tool selection patterns but is not required for a function-calling model to invoke tools. The model still needs tool definitions at inference time to know the current tool names, descriptions, and parameter schemas. Relying on fine-tuning alone leaves the model unable to adapt when tools change and adds training cost and lifecycle overhead without providing the runtime contract needed for invocation.
About these practice questions
This Databricks-GenAI-Assoc question is part of Courseiva's 330-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-GenAI-Assoc practice question is part of Courseiva's free Databricks certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Databricks-GenAI-Assoc exam.