tax.progressive

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

Goes well beyond the readOnly/idempotent annotations: it discloses the bracket boundary convention (lower exclusive, upper inclusive), that per-bracket amounts are summed then rounded, and the defaults for rounding mode and decimals. It doesn't discuss edge cases like zero income or invalid bracket ordering, which keeps it short of a 5.

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-loaded with purpose, then input conventions, then rounding behavior, then the sibling warning — a logical order with no filler. It is dense, packing several rules into long clauses, which costs a bit of readability but no sentence is wasted.

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 values need no explanation; what an agent still needs — input formats, bracket semantics, rounding control, and a warning about policy drift — is all present. Nothing required to call it correctly is missing.

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% and nested bracket items are untyped objects, so the description carries the full burden — and it does: income format, bracket item shape ({upper, rate}), ordering and terminal null rule, rate format, plus defaults for rounding and decimals. This is exactly the compensation the schema gap requires.

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 and resource ('임의의 누진세율 구간표로 세액을 계산한다') and immediately contrasts itself with the policy-driven siblings (kr_income). An agent can tell this is the generic/arbitrary-bracket engine versus the statutory Korean tax tools without opening any schema.

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?

Explicit when-not guidance: hand-entering statutory tables fails to reflect amendments, so prefer kr_income and similar policy-reading tools. It also states the input conventions that make the tool usable (non-negative Decimal string, ascending brackets, last upper null).

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