Exam vs 2026: the gotchas
The exam is fixed to its guide, but the Claude API and Claude Code keep changing. In a few places, the answer the exam wants is no longer how you'd build it today. If you know the current product well, those questions feel wrong. This page lists them, so you can recognise them and answer the way the exam expects.
All domainsChecked against the exam guide and the live API reference, 31 Oct 2026About 15 minutes
At a glance
| # | Topic | Exam answer (follow this) | What's true today |
|---|---|---|---|
| 1 | Guaranteed JSON | A tool with a JSON schema | output_config.format (structured outputs) |
| 2 | Forcing a tool call | tool_choice any or forced are valid | Both return an error on Opus 5.5, Sonnet 5.5 and Fable 5.1 |
| 3 | Spawning subagents | The Task tool; allowedTools must include "Task" | Claude Code calls it the Agent tool |
| 4 | Custom slash commands | .claude/commands/ (shared) vs ~/.claude/commands/ (personal) | Commands are folded into skills |
| 5 | MCP error for a bad argument | A JSON-RPC protocol error | A late-2025 spec revision suggests isError |
| 6 | stop_reason | Two values matter: tool_use and end_turn | Seven values exist |
| 7 | Too many tools | Give each agent only the 4 or 5 tools it needs | Tool search lets one agent have hundreds |
| 8 | Prefill and temperature | Prefill is a wrong option; temperature is barely tested | Both return an error on current models |
The eight, one by one
1 · Guaranteed JSON means “a tool with your schema”
Exam: guide 4.3 says “tool_use with JSON schemas = most reliable schema-compliant output”. You define a tool whose input schema is the shape you want. Claude “calls” it with the extracted values, and those inputs are your JSON. No code runs; the tool is a form Claude fills in.
Today: a dedicated feature, structured outputs (output_config.format), does the same thing without a pretend tool.
Why it's called a tool: the schema guarantee was first built for tool inputs, so that real functions wouldn't break. Developers borrowed it to get clean JSON, and the name stuck.
How to read it: “define a tool with your target schema” means the guaranteed-JSON option.
- Define a tool whose input schema is the invoice schema, and have Claude call it with the extracted values
- Prefill the reply with
{ - Ask for “only valid JSON” and retry when parsing fails
- Put the schema in the prompt and parse the text
2 · tool_choice: any and forced are valid answers
Exam: auto means Claude may reply in text. any means it must call some tool. Forced ({"type":"tool","name":"..."}) means it must call that exact tool.
Today: any and forced return an error on Opus 5.5, Sonnet 5.5 and Fable 5.1. You use auto plus an instruction, or structured outputs.
How to read it: “must always produce the extraction” means forced. “Must use one of these tools but may pick” means any. “May answer in plain text” means auto.
record_invoice call. Fix?
- Add “always use the tool” to the system prompt
- Set
tool_choiceto forcerecord_invoice - Set
tool_choice: "auto" - Retry when the reply has no tool call
3 · Subagents are spawned by the “Task” tool
Exam: guide 1.2 says the Task tool spawns subagents and allowedTools must include "Task". For parallel subagents, the coordinator emits several Task calls in one response.
Today: Claude Code calls this tool Agent.
How to read it: “Task” means the subagent launcher. If a coordinator never delegates, check whether "Task" is missing from allowedTools.
allowedToolsdoesn't include"Task"- The subagents' system prompts are too short
max_tokensis too low- The subagents need their own API keys
4 · Shared slash commands live in .claude/commands/
Exam: project commands in .claude/commands/ are version-controlled and shared with the team. Personal ones go in ~/.claude/commands/. Skills (.claude/skills/ with SKILL.md) are on-demand workflows, and context: fork runs one in an isolated sub-agent.
Today: commands have been folded into skills, and a skill is also a slash command.
How to read it: “team-wide command, available to everyone who clones the repo” means .claude/commands/. “A workflow with its own allowed tools or an isolated context” means a skill.
/review command. Where?
.claude/commands/in the repo~/.claude/commands/on each machine- Root
CLAUDE.md - A commands array in
.claude/config.json
5 · MCP: protocol error vs isError
Exam: if the call itself is broken (unknown tool, missing or invalid argument), the tool never ran, so it's a JSON-RPC protocol error. If the tool ran and its work failed (an API returned 404 or 503), it's a result with isError: true, which the model sees and can act on.
Today: a late-2025 spec revision recommends returning input-validation errors as isError too, so the model can correct its own call.
How to read it: “did the tool run?” If not, it's a protocol error. If it ran and failed, it's isError. The downstream HTTP code doesn't change that.
user_email is missing, (2) the calendar API returns 404 because the user doesn't exist, (3) the calendar API returns 503. How should each be reported?
- All three as
isError - 1 and 2 as protocol errors, 3 as
isError - 1 as a protocol error, 2 and 3 as
isError - All three as protocol errors
6 · stop_reason: only two values matter
Exam: keep looping while stop_reason == "tool_use", and stop at "end_turn".
Today: there are seven values, also including max_tokens, stop_sequence, pause_turn, refusal and model_context_window_exceeded.
How to read it: options that stop the loop when text appears, or after a fixed number of turns, are wrong. stop_reason controls the loop.
- Raise the iteration limit
- Continue while
stop_reasonistool_use, and stop onend_turn - Tell Claude not to write text before tool calls
- Stop when the reply contains the word “done”
stop_reason says whether Claude has finished.7 · Too many tools: scope them per agent
Exam: guide 2.3 says 18 tools degrade selection compared with 4 or 5. Give each subagent only the tools for its role.
Today: tool search (defer_loading) lets an agent have hundreds of tools and load only the ones it searches for.
How to read it: usually the answer is “give each subagent a few tools for its role”. Pick dynamic loading only when an option offers it and the problem is a large connector library.
- Longer descriptions on all 18 tools
- Split the work across subagents, each with the 4 or 5 tools for its role
- Few-shot examples for every tool
- Merge the 18 tools into one generic tool
8 · Prefill and temperature
Exam: prefilling { appears as a wrong option for reliable JSON, because it starts the reply as JSON but doesn't enforce your schema. Temperature is barely tested.
Today: prefill returns an error on current models, and temperature, top_p and top_k return an error on API version 2026-10-21.
How to read it: the exam and today agree here, so never choose prefill as the reliable answer. If an old question uses temperature for consistency, prefer options that change structure (a schema, examples, explicit criteria) over a sampling setting.
Where instinct points the wrong way
These don't depend on product versions. They're habits that feel right and lose marks.
| # | Instinct | Exam answer | Practise |
|---|---|---|---|
| 9 | “Claude can check its own work if it thinks harder” | An independent review instance with a fresh context and no earlier reasoning catches more | Self-review |
| 10 | “Retry until it's valid” | Retry with the specific error. It's useless when the information isn't in the source; use a nullable field or human review | Extraction honesty |
| 11 | “A strict schema means correct data” | A schema fixes syntax, never meaning (totals that don't add up) | Extraction honesty |
| 12 | “Batch everything to save 50%” | Batch only work that can wait up to 24 hours with no time guarantee. Nothing that blocks a person or a merge, and no multi-turn tool calling | Batch or now |
| 13 | “A hook is code, so it's safe” | Only a hook that blocks is enforcement. A hook that adds a flag or logs is not. For tamper-proof rules, put the check inside the tool | Prompt or hook: tool A before tool B |
| 14 | “Code beats prompts, so always pick code” | Only when the question asks for a guarantee. For “improve tool selection” with vague descriptions, better descriptions win | Tool picker |
| 15 | “One CLAUDE.md per folder” | Conventions that cross folders (like **/*.test.tsx) go in .claude/rules/ with glob patterns | Where an instruction lives |
Rule to remember
tool_choice forced or any, the Task tool, .claude/commands/, protocol error vs isError, and stop_reason controlling the loop. Use the newer way only when an option explicitly offers it and nothing else fits.
Related: every API field, with what to study · all traps · CCA-F start here