payroll.kr_national_pension_benefit

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

Annotations already declare readOnly/idempotent/closed-world, and the description adds genuinely new behavioral detail beyond them: monthly payout truncated below 10 won, the Article 53 ceiling on average standard monthly income, the ±0.5%/0.6% per-month adjustment caps of 60 months, and the explicit scope exclusions. That is substantive disclosure about what the computation does and does not capture.

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 formula basis in a single dense paragraph with no filler sentences; every clause carries information. It is somewhat over-packed with statutory constant ranges (2.4–1.29) that an agent does not need in order to call it.

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 12-parameter, formula-heavy domain tool with an output schema present (so return values need no explanation), the description supplies the governing formulas, key parameter conventions, rounding and ceiling rules, and scope limits. The remaining gap is the undocumented semantics of a few secondary parameters.

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 coverage is 0%, so the description must carry all 12 parameters, and it only partially does: year (payment start year), the won-string convention for amounts, and the b_value/monthly_income/income_history choice with revaluation are explained. Several parameters remain undocumented — as_of, include_proposed, deferral_ratio's relationship to claim_offset_months, and the dependent_* fields are only inferable via the dependent family pension mention.

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 — computing the expected Korean national pension old-age benefit — and grounds it in explicit statutory formulas (Art. 51 basic amount with A-value and 2.4–1.29 band constants, Art. 63 payment rate, early/deferral adjustments, dependent family pension). This level of specificity makes it unmistakably distinct from the other payroll.* tax and wage tools in the sibling list.

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?

Gives a clear application context (expected benefit projection) and an explicit when-NOT: it omits credit accrual and the working-person reduction, so it is 'misuse' as a stand-in for the agency's confirmed amount. It does not name an alternative sibling tool to use instead, which keeps it below 5.

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