Audit explanations or answers for concepts beyond a specified Japanese school grade; flags out-of-scope knowledge for grade-limited prompts and marks unregistered terms as undetermined.
説明文や解答に、指定した学年より後で学ぶ既知概念が混ざっていないか監査します。『中2までで説明して』のような制約チェック向けです。未登録概念は安全判定せず未判定にします。
| Name | Required | Description | Default |
|---|---|---|---|
| answer | Yes | 監査したい説明文・解答 | |
| target | Yes | 許可する知識範囲の上限 |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral burden. It usefully discloses a genuine behavioral trait — unregistered concepts are not passed as safe but reported as undetermined — which is non-obvious. However it says nothing about the output shape or the strictness of the grade-boundary comparison, leaving gaps for an annotation-free tool.
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 tight sentences, front-loaded with the core action and then two supporting clarifications. No filler, though the final sentence slightly overlaps purposes already implied by the first.
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?
For a 2-param tool with full schema coverage and no annotations, the description covers purpose, a usage scenario, and one edge-case behavior. It omits any indication of the return value (no output schema exists), which an agent would benefit from knowing before invoking it.
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 100% with only 2 documented params, so the baseline is 3. The description's gloss (auditing a 説明文/解答 against a specified grade's known concepts) mirrors the schema's own descriptions rather than adding new parameter-level meaning.
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?
Concrete verb (監査する/audit) plus a clearly bounded resource: whether an answer's explanation contains known concepts taught after a given grade. The scope sense is distinct from get_prerequisites or search_curriculum, though it doesn't explicitly separate itself from the similarly named classify_knowledge_scope.
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?
It gives a concrete usage context ('中2までで説明して' style constraint checks), so an agent knows this is the constraint-verification tool. It stops short of naming when-not-to-use or explicitly routing to a sibling like classify_knowledge_scope.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.