CCDV-F Agents and the Agent SDK Practice Question
A developer is building a Claude agent using the Anthropic Agent SDK. The agent must be able to fetch the current stock price for a given ticker symbol. The developer defines a tool named 'get_stock_price' with an input schema that requires a single string parameter 'ticker'. During testing, the agent responds with a final text answer containing a plausible-looking price, but the tool is never invoked. Which is the most likely cause?
⚠ Common exam trap
The trap here is assuming that a tool will be called simply because it is defined, without ensuring its description clearly communicates its purpose to the model.
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
✓
The tool description field is missing or too vague, so the model does not understand when to use the tool and instead answers from its own knowledge.
The model selects tools based on their name and description. A missing or vague description means the model lacks the information needed to connect the user's request to the tool, so it answers from its own knowledge instead of calling the tool. Providing a clear, specific description that explains what the tool does and when to use it is critical for reliable tool invocation in the Anthropic Agent SDK.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
The tool description field is missing or too vague, so the model does not understand when to use the tool and instead answers from its own knowledge.
Why this is correct
The model decides which tool to call based primarily on the tool's name and description. If the description is missing or does not clearly explain the tool's purpose, the model may not realize it should call the tool for stock prices and may instead generate a plausible answer from training data. A clear description is essential for reliable tool invocation.
- ✗
The tool's JSON schema uses 'type': 'string' for the 'ticker' parameter, but the agent expects an 'enum' of valid tickers.
Why it's wrong here
An enum restricts the model to a fixed set of values, but it is not required for the tool to be invoked. The model can still call a tool with a free-form string parameter. The absence of an enum would not prevent the tool from being called; it would only limit which values are accepted. This is not the cause of the tool never being invoked.
- ✗
The tool's input schema declares 'ticker' as required, but the model cannot provide a value because the user did not specify a ticker symbol.
Why it's wrong here
In this scenario, the user presumably provided a ticker symbol in the request, otherwise the agent would ask for clarification. Even if the ticker were missing, the model could ask a follow-up question rather than fabricate a price. The required parameter alone does not prevent tool invocation; the model can still call the tool if it has the value.
- ✗
The agent's system prompt does not include the phrase 'You must use tools when available', so the model ignores the tool.
Why it's wrong here
While a system prompt can encourage tool use, the model's decision to call a tool is driven mainly by the tool's description and the user's request. There is no requirement for a specific phrase like 'You must use tools when available'. The absence of such a phrase is not the primary reason the tool is not invoked.
About these practice questions
Courseiva writes every CCDV-F question from scratch — 257 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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 Anthropic exam blueprint
This CCDV-F practice question is part of Courseiva's free Anthropic 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 CCDV-F exam.