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

Annotations only carry the safety profile (readOnly, idempotent, non-destructive, closed-world), while the description adds real behavioral substance: the differential reduction rates (30%/75% for 1 house, 20%/50% for 2+), the statutory eligibility conditions, the 2028-12-31 sunset, and the clawback rule (reduction + interest-equivalent add-back if the rental period falls short of 4/10 years). This is context an agent cannot get from the 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 purpose is front-loaded, followed by statutory anchors, rates, requirements, sunset, a notable carve-out, and clawback — every line carries information, no filler. The bilingual duplication is defensible because the Korean statute terms are the operative references, though it makes the block denser than strictly necessary.

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 10-parameter, output-schema-less statutory judgment tool, the description covers eligibility, rate structure, temporal validity, and consequences well. It still leaves the return shape (boolean vs. rate vs. amount) and a couple of parameter units/functions unstated, which matters more here because there is no output schema to fall back on.

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% across 10 parameters, so the description must carry the meaning — and it largely does, mapping requirements onto params: business registration (§168), minteukbeop registration (§5), 85㎡ cap (exclusive_area_m2), ₩600M standard price (published_price_at_start), 5% rent-increase cap (rent_increase_rate), 1 vs 2+ houses (rental_house_count), long-term-general flag, and the sunset (tax_year). Gaps remain: income_tax_before_reduction is never explained, rental_months is only implied via the 4/10-year clawback, and the unit convention for rent_increase_rate (percent vs decimal) is ambiguous.

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 names a specific verb+resource (judge eligibility and rate of the small-home landlord income tax reduction) and pins it to Special Taxation Act art. 96, so an agent can tell it apart from the generic calc_rental_income_tax / judge_rental_income_tax siblings. It also states its role explicitly as the tax_reduction branch (⑤) of calc_rental_income_tax.

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 says when the tool applies (the §96 registration, 85㎡, ₩600M standard-price, 5% rent-increase conditions) and draws a genuinely useful boundary against 소법 §64의2 separation taxation — cases where the 60% expense deduction / ₩4M credit applies but the §96 reduction does not. It does not, however, explicitly route the agent between this tool and judge_rental_income_tax or calc_rental_income_tax as separate callable alternatives.

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