Relief caps and gates

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

Annotations only cover the safety profile (readOnly/idempotent/non-destructive), and the description goes well beyond them: it discloses the two non-offsetting cap baskets with exact amounts, the 2025-03-14 §133② change and that older 1억/2억 citations are wrong for expropriation, and that down/up contracts or unregistered transfers cause full exclusion under §129. This is exactly the domain behavior an agent could not infer from structured fields.

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 English lead line front-loads the purpose, which is good, but the body is dense bilingual prose with parentheticals, a numbered gate arrow chain, and inline JSON. Most content earns its place, yet the mixed-language, run-on framing could be tightened.

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 complex, high-stakes tax judgment tool with no output schema and 0% schema coverage, the description supplies substantial domain context (caps, baskets, exclusions, statutory basis). The remaining gap is coverage of the prior-4-year carry-in parameters, but overall an agent has enough to call it correctly.

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 parameter meaning. It documents the reductions element shape (조문/감면세액/라벨) and ties unregistered_transfer and contract_price_mismatch to full-exclusion behavior, which is genuine added value. It says nothing about tax_year, prior_4year_reductions, or prior_4year_taking_reductions despite these being central to the five-year cap logic.

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 specific verb+resource: it judges whether transfer-tax reliefs survive the §129 exclusion, §133 aggregate caps, and §127⑦ choose-one gates. It also flags its own role ('전액 비과세 안내를 막는 것'), which is more specific than a bare restatement. It does not, however, explicitly say how it differs from siblings like judge_transfer_reliefs or screen_relief_candidates.

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?

The gating flow (§129 → §133 → §127⑦) implies when the tool applies, and the disclaimer about 'full exemption' guidance hints at its role. But there is no explicit when-to-use vs when-not, and no named alternative among the many judge_* siblings that also deal with transfer reliefs.

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