산출세액 계산

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the bar is lower; the description still adds real behavior by disclosing that years not registered in the system are not computed, which tells the agent to expect a no-result case. It stops short of saying how that failure surfaces (error vs. null) or what the returned result looks like.

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?

Two sentences, no filler, with the core computation and the two tax-type branches front-loaded and the year-registration caveat placed last. Every clause carries information an agent needs.

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 five-parameter computation tool with full schema coverage, strong annotations, and no output schema, the description covers the essential: what is computed, from which input, per tax type, and the registration constraint. The main remaining gap is return-value detail — '누진 구간별로' hints at bracket-level breakdown but does not confirm the output shape.

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 every parameter (taxType, taxBase, year, months, fiscalStart) is already documented with units and roles. The description's mapping of fiscalStart to corporate and year to personal merely restates the schema descriptions, and it never touches the proration semantics of 'months'.

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?

Names a specific verb (계산합니다) and a specific resource (산출세액) and scopes it to exactly the two supported tax types with progressive-bracket computation. It implicitly separates itself from the other calculator siblings (estimate_penalty, entertainment_limit, deemed_interest) by naming the tax types, but never explicitly contrasts with 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?

Usage is only implied: compute output tax from a tax base. The sentence '등록되지 않은 연도는 계산하지 않습니다' is a precondition rather than routing guidance, and no alternative or exclusion is named (e.g., when to use estimate_penalty instead). An agent can infer intent but gets no explicit when/when-not rules.

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