Skip to main content
Glama

jimu (renamed to Tax Compass)

源泉徴収税額(原稿料・講演料・デザイン料など)

jp_withholding_tax_fees
Read-onlyIdempotent

Calculate Japanese withholding income tax (源泉徴収税額, including the special reconstruction surtax / from 2027 the defense surtax) on fees paid to a RESIDENT INDIVIDUAL for manuscripts, lectures, design, illustration, photos for print, translation and similar work (所得税法 第204条第1項第1号 fees). Formula: up to ¥1,000,000 → 10.21%; above → (amount − 1,000,000) × 20.42% + 102,100; yen fractions are dropped. Use it when drafting or checking a Japanese freelance invoice or payment (請求書の源泉徴収・手取り). Handles consumption tax shown separately on the invoice. Does NOT cover lawyers, tax accountants, judicial scriveners (司法書士) and other item-2 professionals, sales agents (外交員), hostesses, prizes, corporations or non-residents — corporations and non-residents return an error. It does not judge whether a payment is such a fee.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "payee_type": "<payee_type>",
      "fee_kind": "<fee_kind>",
      "amount": "<amount>"
    },
    "name": "jp_withholding_tax_fees"
  }
}

Input Schema

NameRequiredDescriptionDefault
amountYes1回に払う報酬(円)。消費税を区分して書いているならその消費税を含めた請求の額
fee_kindYes第1号の報酬の種類(呼ぶ側=利用者が選ぶ):原稿料・講演料・デザイン料・イラスト・印刷物に載せる写真・翻訳・その他の第1号。計算は同じ
payee_typeYes受け取る人(呼ぶ側=利用者が選ぶ)。resident_individual=日本に住む個人(これだけ計算する。corporation・non_resident は対象外の誤りを返す)
income_dateNoその報酬の所得が生ずる日(YYYY-MM-DD・ふつうは仕事を終えた日)。払う日ではない。2027年からの内訳の注意書きを変えるためだけに使い、税額は変わらない
consumption_tax_amountNo請求書に区分して書いた消費税の額(上が true の時だけ)
consumption_tax_separately_statedNo請求書で報酬と消費税の額がはっきり分かれているか(既定 false)

Output Schema

NameRequiredDescriptionDefault
notesYesこの答えに効いた決まり・前提(日本語)
resultYes
doc_urlYes人が読む説明のページ(式・出所・例)。利用者に次に読んでもらう先
sourcesYes
law_as_ofNo出所が書く法令の基準日(例:2026-04-01=令和8年4月1日現在法令等)
checked_onYesCyclix Agents が出所を最後に確かめた日
disclaimerYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/closed-world, so the description rightly spends its space on behavior beyond that: the full rate formula with the ¥1,000,000 breakpoint, 10.21% vs 20.42% + 102,100, yen-fraction dropping, and the surtax change from 2027. It also flags error behavior for out-of-scope payees and notes the income_date parameter changes only the explanatory note, not the tax amount.

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?

Front-loaded with purpose, then formula, then usage trigger, then exclusions — a sensible order an agent can scan. Parenthetical Japanese terms and the legal citation add precision rather than noise; no sentence is redundant.

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

Completeness5/5

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

For a read-only calculator with an output schema (so return values needn't be described), the definition covers formula, rounding, tax-inclusive handling, surtax timeline, unsupported payees and its own judgment limit. Nothing an agent needs in order to call it or route away from it is missing.

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?

With 100% schema coverage the schema already defines amount, fee_kind, payee_type, income_date and both consumption-tax fields, so baseline 3 applies. The description adds real meaning on top: that consumption tax shown separately on the invoice is handled, and that all fee_kind values compute identically, which the enum alone does not convey.

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

Purpose5/5

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

States a specific verb and resource ("Calculate Japanese withholding income tax (源泉徴収税額...)") and pins the exact scope: fees paid to a RESIDENT INDIVIDUAL for manuscripts, lectures, design, illustration, photos, translation under 所得税法 第204条第1項第1号. That legal scoping separates it cleanly from siblings such as jp_invoice_consumption_tax or jp_invoice_amount.

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

Usage Guidelines5/5

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

Gives explicit when-to-use ("when drafting or checking a Japanese freelance invoice or payment (請求書の源泉徴収・手取り)") and explicit when-not-to-use with named exclusions: lawyers, tax accountants, 司法書士 and item-2 professionals, sales agents, hostesses, prizes, corporations, non-residents. It also discloses the failure mode (corporations and non-residents return an error) and its own limitation ("does not judge whether a payment is such a fee"), leaving nothing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources