Free Agent Tools

Can a Japan taxpayer claim a relative living abroad as a dependent, and how much does it save?

japan_overseas_dependents_check

Read-onlyIdempotent

Applies Japan's income tax rules for non-resident relatives (国外居住親族, Income Tax Act art. 84/85 and 2023 + 2026 revisions; rules as of 2026-10-25, NTA Q&A revised 2026-08). Ages 16-29 and 70+ qualify on relationship + remittance proof; ages 30-69 only if studying abroad, disabled, or you sent ¥380,000+ to them in the year (送金関係書類 / 38万円送金書類). Relative income limit ¥620,000 for 2026 (¥580,000 for 2025). Amounts: general ¥380,000, specified 19-22 ¥630,000 (special deduction table above the limit), elderly 70+ ¥480,000, spouse ¥380,000/480,000 by taxpayer income, disability add-on ¥270,000/¥400,000; under 16 no dependent deduction. Valid proof: bank transfer, credit card family card, electronic payment; cash and payments via a third party don't count; 3+ payments allow a statement with first and last records. Returns verdict (eligible | conditional | short_of_380k | not_eligible), route, deductions[], totalDeduction, estimatedIncomeTaxSaving (incl. 2.1% surtax), remittance {minimumTotal, shortfall, sendBy, statementOption}, documents, forms, steps, warnings, NTA sources, disclaimer. Use for 'can I claim my parents abroad', 年末調整国外扶養, sending money home. Educational, not tax advice; not affiliated with the NTA.

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": {
      "relationship": "<relationship>"
    },
    "name": "japan_overseas_dependents_check"
  }
}

Input Schema

Name	Required	Description
`age`	No	Relative's age on Dec 31 of the tax year. Give age or birthDate.
`year`	No	Tax year 2026 (default) or 2025.
`method`	No	How you paid. Default bank. cash / via_representative / joint_account are not valid proof.
`birthDate`	No	YYYY-MM-DD (born Jan 1 counts a year older).
`disability`	No	Disability under Japanese criteria. Default none.
`marginalRate`	No	Your income-tax bracket in percent (5, 10, 20, 23, 33, 40, 45) to estimate the saving.
`relationship`	Yes	Relationship to the taxpayer. parent includes parent-in-law; other = other relative within 6 degrees of blood / 3 of marriage.
`firstLastTotal`	No	Sum of the first and last payments of the year.
`relativeIncome`	No	Relative's total income (合計所得金額) in yen; usually 0 for a non-resident with no Japan-source income.
`studyingAbroad`	No	Relative left Japan to study abroad (ages 30-69 route).
`taxpayerIncome`	No	Your own total income in yen (spouse amounts depend on it).
`remittanceCount`	No	Number of payments (3+ unlocks the statement option).
`remittanceTotal`	No	Yen paid directly to this relative in the year. Omit if unknown → verdict conditional.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only cover the read-only/idempotent safety profile, and the description goes well beyond that: it discloses the ruleset version (as of 2026-10-25, NTA Q&A revised 2026-08), what conditions flip the verdict between eligible/conditional/short_of_380k/not_eligible, and that omitting remittance data yields a conditional result. It also warns which proof types are rejected (cash, third-party payments), which is genuine behavioral guidance.

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

Conciseness4/5

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

Front-loaded with the core rule and the age-band logic before the exhaustive amount table and return-field list, and nearly every clause carries operative detail. The output, however, is a dense semicolon-chained block that is hard to scan, and the enumeration of every deduction amount and return key pushes toward overload.

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 13-parameter tool with no output schema, the description compensates fully: it names the returned fields (verdict, route, deductions[], estimatedIncomeTaxSaving, remittance sub-object, documents, forms, steps, warnings, sources, disclaimer) and notes the 2.1% surtax included in the saving. An agent can call it and interpret the response without further information.

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; the description still adds rule-level meaning by tying parameters to thresholds — the ¥380,000 remittance line, the ¥620,000 relative income limit, the 3+ payments statement option, and the 30-69 age route driven by studying/disability/remittance. It does slightly duplicate the schema's own notes on invalid payment methods.

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: applies Income Tax Act art. 84/85 rules for non-resident dependents and returns an eligibility verdict plus deduction amounts. The legal citations and the enumerated verdict values make it unmistakably distinct from siblings like japan_permanent_residency_check or japan_tax_free_refund_check.

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

Usage Guidelines4/5

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

Explicitly routes usage with example phrasings ('can I claim my parents abroad', 年末調整国外扶養, sending money home) and marks the scope boundary 'Educational, not tax advice'. It never names a sibling as an alternative or states a when-not-to-use condition, so it stops short of a 5.

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

All Free Agent Tools tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.