Korea Payroll & Tax (kkuldogu)

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

With no annotations, the description carries the full behavioral burden, and it does disclose the legal basis (Labor Standards Act) and the four result figures, which implies a side-effect-free computation. It does not state that payout is omitted when monthlyOrdinaryWage is absent, whether results are estimates, or that no records are persisted — meaningful gaps for an unannotated tool.

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?

A single sentence, front-loaded with jurisdiction and legal statute, then the outputs. Every clause earns its place and nothing is repeated from the schema.

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?

Five parameters with only one required, no output schema, and no annotations — so the description properly enumerates the returned values, which is the most important thing an agent needs here. It stops short of covering error behavior (invalid startDate pattern) or the consequence of omitting optional inputs, keeping it just under complete.

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 100% and every parameter carries a description including the basis enum and the two dates, so the baseline is 3. The description adds a small amount of value by mapping inputs to outputs (e.g., 'payout value of unused leave' implies monthlyOrdinaryWage drives that figure; 'next accrual' implies basis/referenceDate), but supplies no syntax or edge-case detail beyond the schema.

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?

The description names a specific resource (South Korea paid annual leave under the Labor Standards Act) and enumerates the exact quantities produced: available days, remaining days, next accrual, and payout value. No explicit verb like 'calculate' appears, but the enumerated outputs make the computational nature unmistakable. It is distinguishable from siblings such as severance_pay or parental_leave_benefit by domain, though it never names those alternatives.

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: citing the Labor Standards Act tells an agent this applies to Korean statutory leave entitlement, but there is no when-to-use/when-not statement and no routing to or away from siblings like parental_leave_benefit. The agent must infer applicability from the domain label alone.

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

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the included deductions and the 2026 NTS simplified withholding table, but it does not explain output format, rounding, or assumptions beyond the deduction list.

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?

The description is a single front-loaded sentence with no redundant filler. Country, employee scope, calculation basis, and included deductions are all established efficiently.

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 six-parameter financial calculator with a fully documented schema but no output schema, the description covers the calculation basis and deductions. It leaves output representation and a few assumptions implicit, but the schema supplies the detailed parameter semantics.

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 six parameters including defaults and the annualSalary/monthlySalary override. The description adds no parameter-specific semantics beyond naming deduction categories, so the baseline of 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?

The description states a specific calculation and resource: South Korean monthly net salary for an employee, including the deductions that produce it. It is clear what the tool computes, but it does not explicitly contrast itself with sibling tools such as social_insurance or retirement_income_tax.

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?

There is no explicit when-to-use statement, no exclusions, and no routing to alternative sibling tools. The agent must infer from the name and description that this is for take-home pay rather than separate insurance, tax, or severance calculations.

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

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

With no annotations, the description carries the burden and does disclose real behavior: benefits are computed month by month and are capped, and the 6+6 scheme is modeled. It omits the cap values, the assumed legal rules, and what the response contains, but for a pure calculator the core behavioral profile is conveyed.

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?

One dense sentence that front-loads the jurisdiction, benefit, and scheme scope with no filler. It is a fragment rather than a well-formed statement, which costs a point, but nothing 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?

For a 5-parameter calculation tool with full schema coverage and no output schema, the description says enough to know what is modeled and that output is monthly with caps. It stops short of specifying the cap amounts or the exact return shape, which an agent might still want.

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 100%, so parameters are already documented, and the description adds only the scheme names (6+6, single parents) that map to the mode enum. It adds no detail on caps, wage basis, or how months/spouseMonths interact, so the 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?

Names the specific benefit (South Korea parental leave benefit from employment insurance) and its computation style (month by month with caps), plus the scheme variants it covers. An agent can tell this apart from siblings like unemployment_benefit or annual_leave. It never uses an explicit verb such as 'calculate', so it reads as a topic label rather than an action, which keeps it from a 5.

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 mention of the 6+6 both-parents scheme and single parents implicitly tells the agent when this tool applies, but there is no explicit 'use this when X, not Y' routing or prerequisite statement relative to siblings. Usage is implied by domain coverage rather than stated.

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

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

With no annotations, the description must carry the behavioral burden; it does disclose the calculation method breakdown, which is helpful. However, it mentions a reduced tax for IRP pension receipt while no corresponding input parameter exists, leaving the agent unsure how that branch is triggered, and it says nothing about output format or determinism.

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?

A single dense sentence with no filler, front-loading the jurisdiction and the resource before listing the computed components. It is efficient, though the clause list is long enough to border on cramming.

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 self-contained calculator with no output schema, the description conveys the scope reasonably well. The gap is the unexplained IRP-pension reduction, which has no input parameter, so an agent cannot tell how to request that calculation.

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 all three parameters (startDate, lastWorkDate, severancePay) are already documented in the schema. The description adds no units, defaults, or format details beyond that, so the baseline of 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?

The description names a specific resource (South Korea retirement income tax on a severance payment) and enumerates the components computed: service-year deduction, converted-pay deduction, national and local tax, and IRP-reduced tax. This clearly separates it from the sibling severance_pay (gross pay) tool, though the verb is implied rather than stated outright.

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 subject matter implies when to use it (taxing a severance payment after leaving a job), but there is no explicit guidance on when to pick this over severance_pay or how the two combine. No exclusions or prerequisites are stated.

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

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

No annotations are provided, so the description carries the full burden. It discloses the core formula and mentions retirement income tax, but it does not say whether the result is gross or net, how service years are rounded, or whether the tool has no side effects.

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?

It is one front-loaded sentence, and every clause (jurisdiction, formula, tax, inputs) is relevant. The density is justified by the statutory calculation being described.

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?

There is no output schema and no annotations, yet the description never states the return shape (gross amount, tax breakdown, or net pay) or key eligibility assumptions. Adequate for a simple calculator, but not fully complete.

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 100% and already documents all five parameters. The description restates the hire date, last working day, and last-3-months pay basis, but it does not explain how annualBonus or annualLeavePay feed into the average wage, so it adds little beyond the schema.

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 the exact statutory benefit (South Korea severance pay) and gives the core formula, so the resource is unambiguous. However, it never uses a clear action verb such as calculate or return, and it does not distinguish itself from siblings like retirement_income_tax.

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?

There is no explicit when-to-use or when-not guidance. Even though 'statutory' and the Korean jurisdiction narrow the domain, the agent is not told whether to call this versus retirement_income_tax or net_pay.

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

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

With no annotations, the description carries the full burden. It helpfully discloses that rates are 2026 and that both employee and employer sides are covered, but it omits important behavioral details like rounding, contribution caps, or whether the result is a total or an itemized breakdown.

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?

A single, front-loaded sentence with no wasted words. It immediately identifies the domain, scope, and rate year.

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 three-parameter calculator with full schema coverage, the description is adequate but thin. It does not describe the return shape or whether the result includes a per-insurance breakdown, which matters because there is no output schema.

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 parameters are already well documented. The description adds only 'monthly wage' context and does not elaborate on how nonTaxable or employerSize affect the calculation beyond what the schema states.

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?

The description clearly states the resource (South Korea's four major social insurances) and what is computed for a monthly wage: employee deductions and employer contributions at 2026 rates. It is distinguishable from siblings like net_pay or severance_pay, though it does not explicitly say 'calculate' and could be sharper about the output being a breakdown.

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 implied by the payroll-calculation context, but there is no explicit guidance on when to choose this tool versus siblings such as net_pay or retirement_income_tax. No exclusions or prerequisites are stated.

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

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that the calculation uses a 2026 cap and floor and returns benefit days and total, but it does not state eligibility assumptions, minimum insured-year rules, validation behavior, or what happens when inputs fall outside the benefit scheme.

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?

The description is a single front-loaded sentence that names the benefit and enumerates the three output quantities. Every phrase contributes to understanding the tool's result.

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 six-parameter calculator with no output schema, the description usefully enumerates the return concepts (daily amount, benefit days, total) and the applicable 2026 cap/floor. It is nearly complete, though it could clarify eligibility or edge-case behavior.

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 all six parameters are already documented in the input schema. The description adds no parameter-level detail beyond what the schema provides, making the baseline 3 appropriate.

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?

The description clearly names the resource (South Korea unemployment benefit / job-seeking allowance) and lists the exact outputs: daily amount with 2026 cap and floor, number of benefit days, and total. It is distinguishable from payroll siblings by domain, though it does not explicitly contrast itself with alternatives.

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?

There is no guidance on when to use this tool versus siblings such as severance_pay or net_pay, nor any mention of eligibility prerequisites or exclusions. The purpose implies its use, but no explicit usage rules are given.

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