인용 조문 점검

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description adds what is actually compared (existence, deletion, 항·호 range) and what is deliberately not evaluated. It does not say what a mismatch report looks like or how mass citations affect runtime, and there is no output schema to fill that gap.

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?

Two sentences: the first front-loads the action, input domain, and comparison target; the second is a single, high-value scope exclusion. No restatement of the tool name and no filler.

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?

Given three simple parameters and no output schema, the agent knows what is checked, against what source, at what time basis (via asOf in the schema), and what is explicitly out of scope. The only shortfall is that the shape of the result — per-citation status list versus aggregate summary — is left implicit.

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%, so draft, asOf, and defaultLaw are already documented in the schema. The description only echoes the input by quoting the citation format ('법인세법 시행령 제89조제3항') and does not explain the effect of asOf or defaultLaw beyond the schema, so the baseline of 3 applies.

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?

States a concrete verb+resource: extract statutory citations from a draft and verify their existence, deletion status, and article/paragraph range against the 법제처 original text. It distinguishes itself from lookup siblings (find_statute, read_provision) by operating on a draft document rather than on a single provision, and it names the boundary case ('같은 법 제52조') it handles.

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 a clear triggering context — 의견서·검토메모·답변 초안 — and an explicit exclusion ('문언의 의미가 맞는지까지는 판단하지 않습니다'), which usefully routes semantic questions to provision-reading/interpretation tools. It never names a specific sibling as the alternative, so the when-not guidance is stated as a scope limit rather than as routing.

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