Skip to main content
Glama

Australian income tax and refund estimate

annual_tax_estimate
Read-onlyIdempotent

Australian income tax for a whole financial year and the likely refund or bill: tax at resident or foreign rates, low income tax offset, seniors and pensioners tax offset, Medicare levy with low-income and family reductions, Medicare levy surcharge and compulsory HELP/study loan repayments, compared with the tax withheld. Applies the $1,000 standard deduction for work-related expenses from 2026-27 and the working Australians tax offset (up to $250) from 2027-28. Use it for tax return estimates and questions involving deductions, other income, overtime, bonuses, couples and families, seniors or private health cover. For per-pay take-home figures use take_home_pay. Supports 2025-26, 2026-27 and 2027-28 (an estimate with no refund). estimatedRefund is positive for a refund and negative for a bill. AUD. Read-only and deterministic.

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": {
      "salary": "<salary>"
    },
    "name": "annual_tax_estimate"
  }
}

Input Schema

NameRequiredDescriptionDefault
bonusNoBonuses paid in the year (AUD).
saptoNoEligible for the seniors and pensioners tax offset, with this status.
familyNoSpouse and dependent children, for the Medicare levy family reduction and surcharge thresholds.
salaryYesSalary or wages for the year from one employer (AUD), excluding super, overtime and bonuses.
taxYearNoFinancial year. Default 2026-27.
overtimeNoOvertime earnings for the year (AUD).
studyLoanNoHas a HELP, VSL, SSL or other study and training support loan. Default false.
deductionsNoWork-related expenses the person would itemise (AUD). From 2026-27 residents with work income get at least the $1,000 standard deduction, so amounts up to $1,000 don't change the result.
otherIncomeNoOther taxable income with no tax withheld, e.g. interest (AUD).
tfnProvidedNoEmployee gave their tax file number. Default true. False applies the no-TFN rate.
payFrequencyNoHow often the salary is paid, for tax withheld. Default fortnightly.
foreignResidentNoForeign resident for tax purposes. Default false.
otherDeductionsNoDeductions not covered by the standard deduction, such as gifts to charity and tax agent fees (AUD).
taxFreeThresholdNoTax-free threshold claimed with this employer. Default true (main job). Use false for a second job.
salaryIncludesSuperNosalary is a package including the 12% super guarantee.
privateHospitalCoverNoHas private patient hospital cover all year. Default true (no Medicare levy surcharge).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / deductions / description
      Previous value: -"Tax deductions (AUD)."New value: +"Work-related expenses the person would itemise (AUD). From 2026-27 residents with work income get at least the $1,000 standard deduction, so amounts up to $1,000 don't change the result."
    • addedInput schema / properties / otherDeductions
      Added value: +{
      +  "description": "Deductions not covered by the standard deduction, such as gifts to charity and tax agent fees (AUD).",
      +  "minimum": 0,
      +  "type": "number"
      +}
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds real behavior: AUD only, deterministic, the sign convention of estimatedRefund, the fact that 2027-28 returns an estimate with no refund, and the rule changes applying from 2026-27 and 2027-28. The only wasted clause is 'Read-only and deterministic', which partly repeats the annotations.

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 is front-loaded and the alternative-tool routing sits early, and nearly every clause carries information. However, the opening sentence is a long comma-chained list of offsets and levies, and the supported-years note is buried mid-paragraph rather than grouped with the other constraints.

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 16-parameter nested tool with no output schema, the description covers the essentials: currency, determinism, supported years, the meaning and sign of estimatedRefund, and the boundary against sibling tools. Nothing an agent needs in order to call this correctly is missing.

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

Parameters3/5

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

Schema coverage is 100% with enums and per-field descriptions, so the schema already carries the parameter burden. The description restates the $1,000 standard deduction and working Australians tax offset, both of which are already documented on `deductions`, and adds no syntax, defaults, or interaction rules beyond that. Baseline 3 is appropriate.

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 — annual Australian income tax plus the resulting refund or bill — and enumerates the components (Medicare levy, surcharge, HELP, offsets) so the scope is unambiguous. It also names the sibling it is not (take_home_pay), so an agent can separate annual estimation from per-pay calculation without opening a schema.

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 use cases (tax return estimates, deductions, other income, overtime, bonuses, couples, seniors, private health cover) and an explicit exclusion with the alternative: 'For per-pay take-home figures use take_home_pay.' It also bounds the supported years, which doubles as a when-not condition.

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.