Skip to main content
Glama

日本の給与・社会保険・労働法

by io.github.kishida-devil

給与計算 — 社会保険料・源泉所得税・手取り

calculate_payslip

Full monthly deduction breakdown for one employee: health insurance, long-term care, pension, child support, employment insurance, withholding income tax and net pay, with the employer share as well.

Use this rather than computing it yourself. Premiums are charged on 標準報酬月額 — a 50-grade step function — and not on actual salary, while employment insurance IS charged on actual salary; the employee share rounds half DOWN; pension stops at grade 32; long-term care applies only from 40 to 64. Income tax is computed on pay after social insurance, which the tool derives internally, so do not pre-deduct it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ageNoAge in years. Either this or birth_date is required — long-term care is charged only from 40 to 64, so the premium cannot be settled without it. Prefer birth_date.
as_ofNoThe premium month: an ISO date in the month the person is insured for, NOT the pay date. Employers may deduct the previous month's premium from this month's pay (Health Insurance Act art. 167), so with next-month deduction pass a date in the month before the pay date. Drives the age milestones and picks the rate table; a date outside the published period returns 422 rather than the current table.
columnNo甲 if the employee filed a 扶養控除等申告書 (the normal case), 乙 if not. Defaults to 甲.
birth_dateNoDate of birth, YYYY-MM-DD. Strongly preferred over `age`: 年齢計算ニ関スル法律 puts the attainment of an age on the day *before* the birthday, so someone born on the 1st of a month crosses a threshold in the previous month and their premium changes a month earlier than a naive calculation gives.
dependantsNo源泉控除対象親族の数. Defaults to 0.
income_taxNoSet false to skip withholding tax. Defaults to true.
prefectureYesPrefecture of the employer's 適用事業所 — English ("Tokyo"), Japanese ("東京" or "東京都"), or JIS code 1-47. Health insurance rates differ by prefecture; pension does not.
resident_taxNoResident tax to deduct, in yen. It is levied by the municipality on the previous year's income and is never derived here — pass the figure from the 特別徴収税額通知書.
business_typeNoEmployment insurance rate band. Defaults to general.
commuting_fareNoReasonable fare or toll paid on top of a car or bicycle commute. With commuting_distance_km the ceiling is the distance band plus this, capped at 150,000.
monthly_salaryYesGross monthly pay in yen, before any deduction.
employment_typeNo役員 are not employment-insurance insured (雇用保険法第4条). Pass "director" for a company officer, or the premium comes out too high. Defaults to employee.
commuting_parkingNoMonthly parking the employee pays for a car or bicycle commute, in yen. Added to the distance band up to 5,000 a month. Needs commuting_distance_km — there is no band to add it to for someone who commutes only by train.
workers_comp_typeNo労災保険 事業の種類の番号, e.g. "98" for wholesale/retail/restaurants/hotels. Workers compensation falls entirely on the employer and is left out unless you pass this, because rates run from 2.5/1000 to 88/1000 and there is no safe default. list_workers_compensation_rates has the table.
commuting_allowanceNoCommuting allowance in yen per month. Social insurance counts it as remuneration in full, income tax exempts it up to a ceiling — 150,000 a month by public transport. Do NOT fold it into monthly_salary: doing so taxes it, and leaving it out understates the premiums. The split comes back in earnings.items.
commuting_distance_kmNoOne-way distance for a car or bicycle commute. The exempt ceiling then comes from the distance table (国税庁 No.2585) rather than the 150,000 transit ceiling; under 2 km nothing is exempt.
standard_remunerationNoThe 標準報酬月額 fixed by 算定基礎届 or 月額変更届. Pass it whenever it is known. Without it the grade is re-derived from the pay you send, which is wrong in any month with overtime — a 300,000 yen earner who made 369,469 in a busy month is over-deducted by 8,445 yen. decide_regular_determination returns the right figure.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and succeeds: it discloses the 標準報酬月額 step-function basis, the actual-salary basis for employment insurance, half-down rounding, the grade-32 pension stop, the 40-64 long-term care condition, and that income tax is derived after social insurance. These are non-obvious behaviors an agent must know before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three purposeful sentences: the scope/result, the instruction to prefer the tool, and the key computation rules. It is front-loaded with the most important information and every sentence earns its place given the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description lists the output components and the crucial calculation rules, and the schema's per-parameter descriptions are rich enough to fill remaining invocation details. It lacks an explicit output shape and sibling routing, but those are not fatal given the schema's quality.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful cross-parameter logic: premiums use standard remuneration while employment insurance uses actual salary, income tax must not be pre-deducted, and age restrictions gate long-term care. This supplements the per-parameter schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear subject-verb-resource: 'Full monthly deduction breakdown for one employee' and enumerates components, including employer share. It implicitly distinguishes this from siblings like calculate_bonus or calculate_payroll_batch by saying 'monthly' and 'one employee,' but it never names an alternative or states what it is not.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use this rather than computing it yourself' and 'do not pre-deduct it' give some usage direction. However, with many payroll siblings, the description provides no explicit when-to-use versus alternatives (e.g., withholding-tax-only, bonus, or batch payroll).

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

All 日本の給与・社会保険・労働法 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation4/5

Most tools have distinct, well-defined jobs—payroll calculations, revision judgments, eligibility checks, and data lookups are clearly separated. The main remaining risk is among the standard-remuneration judgment tools and the batch/singleton pairs, but their descriptions are detailed enough to prevent serious misselection.

Naming Consistency3/5

There is a reasonably recognizable pattern with calculate_, judge_, check_, get_, and validate_ groups. However, several noun-phrase names (business_days, consumption_tax, national_insurance, commuting_allowance_exemption) and overlapping verb choices (decide_ vs judge_ vs check_) prevent a fully consistent verb_noun convention.

Tool Count2/5

At 30 tools, the surface is materially larger than the 3–15 range that keeps an agent's selection burden low. Batch variants and three separate standard-remuneration revision tools add complexity, and although the domain is broad, the count feels heavy for an assistant to choose from confidently.

Completeness4/5

The core workflows are well covered: monthly pay, bonuses, overtime, standard-remuneration determination, year-end adjustment, resident tax, leave, worker classification, and invoice validation. Gaps exist around statutory benefit payments such as sickness or maternity allowances and retirement-specific processing, but most payroll and social insurance tasks can be completed without dead ends.

Resources