realestate.kr_local_property

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

Annotations already declare readOnly/idempotent/closed-world, and the description adds substantive computed behavior: truncation vs bracket-rounding rules for acquisition vs property tax, and the important caveat that metropolitan coefficients are representative values only for district-level ordinance matters. This is real behavioral context beyond annotations, though the treatment of the undocumented optional flags' effects is absent.

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?

Front-loads the purpose and scope, then layers rounding rules and caveats without much redundancy. Dense but every sentence adds either scope, computation semantics, or a caveat; minor verbosity in the region enumeration.

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?

An output schema exists so return-value explanation isn't required, and the caveats are strong. However, with 6 of 9 parameters undocumented at 0% schema coverage, the definition is not complete enough for an agent to confidently set is_one_house, include_urban, or include_proposed without guessing.

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% with 9 parameters, so the description carries the burden but only clarifies three: mode values (acquisition/property), price format (원 단위 문자열), and region list. Highly consequential params like is_one_house, include_urban, is_one_house, area_m2, year, as_of, and include_proposed are left undocumented, a significant gap for tax computation.

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 (계산한다) and resource (주택 취득세 또는 재산세), scoped to metropolitan municipalities with ordinance adjustment coefficients. An agent can tell it computes local-level acquisition/property tax, though it doesn't explicitly name the sibling kr_acquisition_tax or kr_property_tax to distinguish the local variant.

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?

Provides a clear misuse exclusion ('구·군 단위 세율 확정에 사용' is a misuse example) and explains mode selection between acquisition and property. It doesn't name the alternative tool to use when district-level precision is needed, leaving that routing to inference.

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