Skip to main content
Glama

Calculate.co.nz NZ Calculators

nz_minimum_wage_calculator

Give the New Zealand minimum wage in force on a date, the pay for given hours, and the take-home after PAYE, ACC, KiwiSaver and student loan.

Use for: 'what is the minimum wage nz', 'minimum wage 2026', 'minimum wage
take home pay', 'starting out wage', 'training wage nz', 'minimum wage per
week', 'what was the minimum wage in 2020', 'youth rates nz'.

THREE RATES, TWO OF THEM THE SAME. Adult is $23.95 an hour from 1 April
2026. Starting-out and training are both 80% of the adult rate, $19.16.
Per Employment New Zealand, starting-out covers three groups: 16 and 17
year olds who have not worked 6 continuous months for their current
employer; 16 to 19 year olds whose employment agreement requires at least
40 credits a year of industry training; and 18 and 19 year olds paid a
specified benefit for 6 months or more who have not since worked 6
continuous months for one employer. Training covers those 20 and over
whose agreement requires at least 60 credits a year of industry training,
usually apprentices. Neither applies to anyone supervising or training
other workers. Before 1 May 2013 the 80% rate was the new entrant rate,
and rate_name says so.

THE RATE CHANGES EACH 1 APRIL. In March the rate in force is last year's.
Give as_at to answer for any date from 1 April 2008.

TAKE-HOME IS ON CURRENT SETTINGS ONLY, so for a past date the take_home
field is null and only the rate and gross pay are given.

Tax code M does not claim the IETC: 40 hours at $23.95 nets $761.06 a week
on M, $771.06 on ME.

Args:
    wage_type: adult, starting_out, training, living_wage or custom.
    hours_per_week: Hours worked a week, more than 0 and at most 168.
    custom_rate: Hourly rate, required when wage_type is custom.
    kiwisaver_rate: Employee rate as a fraction (0.035 for 3.5%), or 0.
    student_loan: Whether a student loan is being repaid.
    tax_code: M, or ME for someone eligible for the IETC.
    as_at: Date to answer for, ISO YYYY-MM-DD. Defaults to today in NZ.

Returns:
    The rate applied and its effective date, the adult, starting-out and
    training rates on that date, gross weekly, fortnightly and annual pay,
    the take-home breakdown, a 40 hour comparison of the rates, and the full
    dated history.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "nz_minimum_wage_calculator"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_atNo
tax_codeNoM
wage_typeNoadult
custom_rateNo
student_loanNo
hours_per_weekNo
kiwisaver_rateNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations at all, the description carries the full burden and does so: it discloses that take_home is null for past dates because it is computed on current settings only, that the rate changes each 1 April so March reflects last year's rate, that as_at supports any date since 1 April 2008, and the M-vs-ME IETC distinction. These are non-obvious behaviors an agent could not infer from the schema.

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?

Purpose and use cases are front-loaded, then rate mechanics, then Args and Returns. It is long, and the multi-clause eligibility paragraph for starting-out/training could be tightened, but nearly every sentence earns its place by disambiguating an enum choice or a historical-date behavior.

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?

There is no output schema, so the description supplies a Returns section enumerating the rate, effective date, all three rates, gross weekly/fortnightly/annual pay, take-home breakdown, a 40-hour comparison and dated history. Combined with the historical-dating and current-settings caveats, an agent has everything needed to call it and interpret the response.

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?

Schema description coverage is 0%, so the description must compensate, and the 'Args:' block documents all seven parameters: bounds on hours_per_week (more than 0, at most 168), custom_rate being required when wage_type is custom, kiwisaver_rate as a fraction with an example, student_loan, tax_code M/ME, and as_at as ISO date defaulting to today in NZ. It also explains the eligibility rules behind starting_out vs training, which is the only way an agent can pick the right enum value.

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?

First sentence states a specific verb+resource: the NZ minimum wage in force on a date, plus gross pay and take-home. The scope (three statutory rates, historical dating from 1 April 2008) makes it unmistakably distinct from generic siblings like nz_paye_calculator or nz_hourly_to_salary_calculator, which do not model the statutory rate schedule.

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?

The 'Use for:' list of literal queries ('minimum wage 2026', 'starting out wage', 'what was the minimum wage in 2020') gives strong positive routing signals. There are no explicit exclusions or named alternatives (e.g. 'for take-home on an arbitrary rate, use nz_paye_calculator'), which keeps it 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources