compare_outcomes

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

Beyond the annotations (readOnly/idempotent/openWorld/destructive=false), it discloses that outcome verdicts are read from the 본문 주문·결론 by rule and not model-inferred, that arguments/reasons are cut excerpts from the body, the explain-mode behavior (host_ai vs solar_cloud/onprem), and a latency of roughly 5–10 seconds. That is rich behavioral context, though it doesn't discuss failure modes or result limits beyond the n cap.

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?

The purpose is front-loaded and the body is information-dense with labeled sections (언제 / 결과 판정 / 반환 / explain). It is bilingual and the two language blocks largely mirror each other, which adds length, but for a Korean-first tool this is largely functional rather than 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?

There is no output schema, so the description carries the return-value burden and does so by enumerating the return shape (쟁점, 집계, 납세자 승/일부 인용/패, 각하·기타, 갈린 지점?, mode?, 주의). Combined with the mode and latency disclosures, an agent has nearly everything needed to call it correctly; missing only explicit limits on result volume beyond n.

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 the schema already documents n, tax, lang, issue and explain, giving a baseline of 3. The description adds a little on explain's mode-dependent behavior but does not add format or syntax meaning beyond what the schema text already provides.

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 states a specific verb and resource: it splits decisions on one issue into taxpayer-won / partial / lost and lays out both sides' arguments plus the deciding reasoning ('납세자 승(인용·취소)/일부 인용/패(기각)'). It is concrete about what is produced, but it never names or distinguishes a sibling like compare_with_case or research_issue, so an agent must infer the boundary from the schemas.

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 explicit context: use it in 불복·조사 대응 when you want to see what the winning side proved and what the losing side lacked, with the explicit constraint not to filter only winning cases (both sides must be shown). This is useful when-to-use guidance, though no alternative tool is named as a fallback.

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