Skip to main content
Glama

Calculate.co.nz NZ Calculators

nz_tax_refund_calculator

Estimate a New Zealand income tax refund, or tax owed, for a year.

Use this for ANY question about a NZ tax refund or an end of year tax bill.

Common use cases: 'am I owed a tax refund', 'I only worked part of the year,
do I get money back', 'I had a second job on an S code, was I overtaxed',
'how much tax should I have paid on 62k'.

A refund is what was deducted minus what was actually owed. PAYE comes out of
each pay as though that pay continued all year, so the two usual causes of a
refund are a part year and a second job on a flat secondary code. Both are
broken out in the result, and both are already inside refund_or_bill rather
than additional to it.

ASK FOR THE PAYE FIGURE if you can. paye_deducted from payslips or an IRD
summary gives a real answer; leaving it out estimates it from the tax code
and months worked, which is much rougher. Also ask whether that figure
includes ACC, because most payslips lump the earner levy in with PAYE and it
is not income tax.

Args:
    gross_income: Total gross income for the year, before tax, in NZD.
    tax_year: 2026-27, 2025-26, 2024-25 or 2023-24. 2024-25 is approximate
        because thresholds moved part way through it.
    paye_deducted: Total PAYE deducted for the year. None to estimate it.
    acc_included_in_paye: Whether ACC is inside that figure. Usually yes.
    tax_code: M, ME, MSL, or a secondary code. Only used when estimating.
    months_worked: Months actually worked. Often the whole reason for a refund.
    secondary_income: Income from a second job on a secondary code.
    secondary_tax_code: SB, S, SH or ST.
    donations: Donations to approved donee organisations.
    student_loan_deducted: Repayments deducted, or None for no loan.
    ietc_eligible: False for a main benefit, Working for Families or NZ Super.

Returns:
    refund_or_bill, POSITIVE for a refund owed to the person and NEGATIVE for
    tax they owe, with is_refund saying which. Also the correct tax, the
    IETC, ACC, and the part year and secondary components of the difference.
    The donations credit and student loan square up are returned but are NOT
    inside refund_or_bill, because IRD settles those separately.

Salary and wages only. IRD issues an automatic assessment for most people and
that figure is the one that counts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tax_codeNoM
tax_yearNo2026-27
donationsNo
gross_incomeYes
ietc_eligibleNo
months_workedNo
paye_deductedNo
secondary_incomeNo
secondary_tax_codeNoS
acc_included_in_payeNo
student_loan_deductedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations present, the description carries the full behavioral burden and does so thoroughly: it explains the refund logic, warns that omitting paye_deducted produces a rougher estimate, flags the ACC-in-PAYE issue, and documents that donations and student loan amounts are returned separately rather than included in refund_or_bill.

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?

The description is long, but every section earns its place: quick purpose, common use cases, calculation logic, the critical PAYE/ACC request, parameter explanations, and return semantics. Key information is front-loaded and the structured Args/Returns layout makes it easy to scan.

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?

Given 11 parameters, no output schema, and no annotations, the description is complete: it covers all parameters, return values and their sign convention, which components are included versus separate, approximation caveats, and the salary-and-wages scope.

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

Parameters5/5

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

The schema has 0% description coverage, and the Args section compensates by adding meaning to all 11 parameters: why months_worked matters, when tax_code is only used, what 'None' means for paye_deducted, and which values are valid for tax_year and secondary_tax_code.

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?

The opening sentence names the exact verb and resource: 'Estimate a New Zealand income tax refund, or tax owed, for a year.' It clearly distinguishes this end-of-year reconciliation tool from sibling calculators through the refund/end-of-year tax bill framing and concrete use cases.

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?

It explicitly says to use this for ANY question about a NZ tax refund or end-of-year tax bill and gives realistic common use cases, plus the exclusion 'Salary and wages only.' It does not name sibling alternatives for adjacent cases such as ongoing PAYE or bonus tax, so the guidance stops short of full when-not/alternative routing.

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