오답 진단

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds the genuinely useful behavioral fact that the tool is conversational/iterative and that the plan only materializes once next_question becomes null. It does not describe the shape of plan or what happens on malformed input, so the added context is moderate rather than rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the purpose then the two-phase protocol in chronological order. No filler, though the parenthetical glosses make individual sentences long enough to require a second read.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must explain return values — and it does, naming next_question and plan and the termination condition. The remaining gap is the internal structure of plan and the index semantics of the integer arrays, which an agent would still have to discover by calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the parameter burden. It does define the three answer categories (known=설명 가능, confused=헷갈림, asked=넘어감 포함 이미 물어본 것), which is real value, but it never explains that these are integer arrays or how the integers relate to items — the most important ambiguity for actually invoking the tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"틀린 문제 목록으로 진단한다" states a specific verb (진단한다) and resource (틀린 문제 목록), and the follow-up sentences make the multi-turn diagnostic flow concrete (next_question, then plan). It is clearly distinct from concept-lookup siblings like get_concept or get_prerequisite_path, though it never names or contrasts them explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives unusually concrete call sequencing: first call with items only, then call again with known/confused/asked populated, and repeat until next_question is null. It does not name alternatives or state when a sibling (e.g. rank_shared_prerequisites) should be used instead, which keeps it below a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.