invoice_penalty

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: the applicable rates, that the rate depends on the supply date, and the legal basis (부가가치세법 제60조).

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 tool's identity and rate table, then uses labeled 언제/입력/결과 sections that make it scannable. Dense but every clause carries information; no wasted 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?

With no output schema, the description usefully discloses what is returned (penalty amount, applied rate, legal basis). Inputs, trigger, and output are all covered, leaving only minor gaps like rounding or multi-year handling.

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 all three parameters. The description largely restates the same mapping (supply_amount, kind, supplied_on) without adding syntax or format detail beyond the schema's own '세율 기준 연도' note, so baseline 3 applies.

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 (구한다/compute) and a precise resource (세금계산서 가산세) and even enumerates the penalty types and rates it handles. The scope is clearly distinct from the other penalty siblings (underreporting_penalty, late_payment_penalty), though it never explicitly names them.

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 '언제:' clause gives an explicit trigger condition — when the invoice issuance/receipt obligation is violated. This is clear usage context, but there is no 'when-not' guidance and no named alternative tool to route against.

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