Tool descriptions, structured tool errors, tool_choice, MCP server setup and scope, Claude Code's built-in tools. About 18% of scored items, by the official exam guide.
Know cold
One idea per card. Open the ones you aren't sure of.
Descriptions pick the tool
Say what it does, what goes in, what comes out, and when to use it instead of its neighbour. "Searches." is not a description.
Errors need structure
Return isError: true with a category, whether a retry could help, and a readable message. An empty result must mean "nothing found", never "couldn't look".
tool_choice has four modes
auto (the default when tools are given; the model may answer in text), any (must call one tool, model picks), tool with a name (must call that tool), none. Forcing isn't supported everywhere: the docs list models where any and tool return a 400 and point to auto with strict tool use or structured outputs instead.
MCP scope
A .mcp.json at the repo root is project scope, shared through git. Reference secrets as ${VAR}; Claude Code expands them. Never commit the value.
Built-in tools
Read a known file. Write creates or overwrites. Edit changes a string in place; old_string must be unique, so add surrounding context, or set replace_all to change every match. Bash runs shell commands. Grep searches inside files. Glob matches names and paths. On macOS and Linux, current Claude Code may run searches as find and grep through Bash, but the content-versus-path split is what gets tested.
Traps
One empty answer for two situations. If [] means both "none" and "the lookup failed", the agent will tell people they have nothing. Failures return isError: true.
Glob for content, Grep for paths. Swapped tools find the wrong files. Grep looks inside files; Glob matches names and paths.
"The repo is private, so the token is fine". A token in a committed file is a committed secret. Use ${VAR} in .mcp.json.
Assuming forcing works on every model. Forced any and tool return a 400 on some newer models. Check the model before relying on it.
Practice: 4 questions
Q5 · Domain 2 · Tool Design & MCP Integration
An intake service has three tools: extract_invoice, extract_receipt and extract_contract. You don't know which kind of document will arrive, but every response must be one of those tool calls, never prose. Your model supports forced tool use. Which tool_choice fits?
A. {"type": "auto"}
B. {"type": "any"}
C. {"type": "tool", "name": "extract_invoice"}
D. {"type": "none"}
Answer and explanation
Answer: B. "any" means the model must call one of the tools and picks which. "auto" lets it answer in text. "tool" forces one named tool, which is wrong for two of the three document types. "none" turns tools off. Check model support before relying on forcing: Anthropic's docs list newer models where "any" and "tool" return a 400, and point to "auto" with strict tool use or structured outputs instead.
A. auto lets the model answer in plain text, which the scenario rules out.
B. Right. any means the model must call one of the tools and picks which. Check model support before relying on it: the docs list newer models where any and tool return a 400.
C. tool forces one named tool, which is wrong for two of the three document types.
D. none turns tools off, so every response would be prose.
Q6 · Domain 2 · Tool Design & MCP Integration
A get_shipments MCP tool returns an empty list both when a customer has no shipments and when the carrier API times out. During an outage the agent tells customers they have nothing on the way. What should change?
A. Add a prompt line: "If the shipment list comes back empty, tell the customer to try again later."
B. Retry inside the tool up to five times, and return an empty list if the call still fails.
C. On failure, return isError: true, a category, a retryable flag and a message. [] means none.
D. Remove the tool entirely and have the agent ask each customer for their tracking numbers instead.
Answer and explanation
Answer: C. The agent can't tell "nothing found" from "couldn't look" because the tool gives the same answer for both. A structured error lets it say the right thing and decide whether to retry. The prompt line wrongly treats every real empty result as an outage, silent retries still hide the failure, and removing the tool throws away a working lookup.
A. This treats every real empty result as an outage, so customers who have nothing on the way get told to try again.
B. After the retries it still returns an empty list, so the failure is still hidden.
C. Right. The agent can't tell "nothing found" from "couldn't look" while both come back as []. A structured error lets it say the right thing and decide whether to retry.
D. Removing the tool throws away a lookup that works whenever the carrier API is up.
Q7 · Domain 2 · Tool Design & MCP Integration
In a large repo you need two lists: every file that calls chargeCard(, and every .json file inside any fixtures/ folder. Which pairing of Claude Code's built-in tools matches the two jobs?
A. Grep for chargeCard( since it's file content; Glob for **/fixtures/**/*.json since it's a path.
B. Glob for *chargeCard* to find the callers, and Glob for **/fixtures/**/*.json to find the data files.
C. Grep for chargeCard( to find the callers, and Grep for the word fixtures to find the data files.
D. Read every source file one at a time and note down the matches for both of the lists by hand.
Answer and explanation
Answer: A. Grep searches inside files; Glob matches file names and paths. Globbing for the function name only finds files whose names contain it. Grepping for "fixtures" finds files that mention the word, not files that live in that folder. Reading everything burns context. On macOS and Linux, current Claude Code may run these searches as find and grep through Bash, but the content-versus-path split is the same.
A. Right. Grep searches inside files and Glob matches file names and paths, so each job goes to the tool built for it.
B. Globbing for the function name only finds files whose names contain it, not files that call it.
C. Grepping for "fixtures" finds files that mention the word, not files that live in that folder.
D. Reading every file by hand burns context on work the search tools do directly.
Q8 · Domain 2 · Tool Design & MCP Integration
Your team wants an MCP server for its issue tracker to be available to everyone who clones the repo. The server needs an API token. What is the right setup?
A. Each developer adds the server to their own ~/.claude.json and pastes the token into it.
B. Commit .mcp.json with the token written inline, since the repository is private anyway.
C. Describe the server and where the token lives in CLAUDE.md so Claude can set it up.
D. Commit .mcp.json with the token as ${TRACKER_TOKEN}; each developer sets it locally.
Answer and explanation
Answer: D. Project scope, a .mcp.json at the repo root, is how a server is shared through git, and Claude Code expands ${VAR} references in it. A per-user config isn't shared. An inline token is a committed secret whatever the repo's visibility. A note in CLAUDE.md is advice, not configuration.
A. A per-user config isn't shared through git, so every developer sets the server up alone.
B. An inline token is a committed secret, whatever the repo's visibility.
C. A note in CLAUDE.md is advice, not configuration. Nothing gets set up.
D. Right. A .mcp.json at the repo root is project scope and is shared through git. Claude Code expands ${VAR} references in it, so the token stays on each developer's machine.
I use Google Analytics to see how people find this site. Nothing is stored unless you agree. What I collect.