verify_local_tax_citations

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

No annotations are provided, so the description carries the burden. It discloses that it performs batch verification against real records (실존 여부), which is useful behavioral context. However, it doesn't describe output format, whether it's a read-only operation, rate limits, or what happens when citations don't exist—though the nature as a verification tool makes read-only fairly inferable.

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, zero waste. Front-loaded with the core verification function and format pattern, then the usage timing. Every word earns its place.

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 verification tool that takes text and checks citations, the description adequately covers the core purpose and invocation timing. No output schema exists, so the description could ideally mention return format or what 'validated' output looks like. But given the relatively simple input (text) and clear purpose, this is nearly complete for the tool's complexity level.

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 coverage is 50% (text documented, oc undocumented). The description adds context that 'text' is the content to verify (사유서 초안 등) and describes what it extracts. However, the 'oc' parameter is completely undocumented—the description doesn't clarify what 'oc' means, leaving the agent to guess. With only 50% coverage and a silent parameter, baseline 3 is appropriate but not higher.

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?

The description clearly states it extracts local tax case numbers (조심 ****지****/****방**** format) from text and batch-verifies their real existence. The verb '일괄 검증한다' (batch verify) plus the specific resource (조세심판원 지방세 사건번호) makes it distinct from siblings like search_local_tax_decisions (searching) or get_local_tax_decision (retrieving one).

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?

States when to call it: '사유서·검토조서 확정 직전에 호출할 것' (call before finalizing reason documents/review memos). This gives clear timing context. However, it doesn't explicitly state when NOT to use it or name alternative tools, though the verification-vs-search distinction is fairly implied by the description.

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