United States Salary Calculator

Net salary in United States (2026)

net_salary

Read-onlyIdempotent

Take-home pay for an employee in United States from a gross yearly salary in USD, with 2026 rules: every tax and contribution itemised with its local name, the effective and marginal rate, employer cost and the step-by-step workings. Covers: 2026 federal brackets: single, married filing jointly, head of household; Child Tax Credit with phase-out and refundable part; FICA with the 2026 wage base and Additional Medicare; 401(k) (with 50+ catch-up), HSA and section 125 pre-tax deductions; State income tax 2026 for 12 states incl. NYC with their own married-couple tables, exemptions and credits; Employee payroll programmes: CA SDI, NY PFL and DBL, NJ TDI/FLI/UI, MA and WA PFML, WA Cares.

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": {
      "gross_annual": "<gross_annual>"
    },
    "name": "net_salary"
  }
}

Input Schema

Name	Required	Description
`age`	No	Age; changes the result here (young-worker reliefs, senior slabs, surcharges). Default 35.
`hsa`	No	HSA contribution. Health Savings Account, 2026 limit $4,400 self-only, $8,750 family. Free of income tax and FICA through payroll. ($ / year). Default 0.
`state`	No	State: none = No state income tax (TX, FL, NV, TN, SD, WY, AK, NH); CA = California; NY = New York (outside NYC); NYC = New York City; IL = Illinois (4.95% flat); MA = Massachusetts (5%, 9% above $1.08M); PA = Pennsylvania (3.07% flat); NJ = New Jersey; CO = Colorado (4.4% flat); NC = North Carolina (3.99% flat); GA = Georgia (4.99% flat); AZ = Arizona (2.5% flat); WA = Washington (no income tax, WA Cares + PFML). Default none.
`filing`	No	Filing status (unmarried). Married people file jointly here; switch on "Married" above.: single = Single; hoh = Head of household (with a qualifying child). Default single.
`pretax`	No	Other pre-tax deductions. Employee share of health premiums, FSA, commuter benefits (section 125): free of income tax and FICA. ($ / year). Default 0.
`married`	No	Married or registered partner. Default false.
`children`	No	Number of dependent children. Default 0.
`fx_per_eur`	No	Exchange rate: 1 euro = this many USD, for the euro amounts. Default 1.08 (indicative).
`pension_pct`	No	Voluntary employee pension contribution through payroll, % of salary. Default 0.
`bonus_annual`	No	Yearly bonus in USD. Default 0.
`gross_annual`	Yes	Gross yearly salary in USD, without bonus
`spouse_income`	No	Partner's gross yearly income in USD, for joint taxation and spouse allowances. Default 0.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A3.7/5.0

Behavior4/5

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

The annotations already declare this a read-only, idempotent, non-destructive, closed-world calculation, so safety is covered. Beyond that the description usefully discloses what the response contains — every tax and contribution itemised with its local name, effective and marginal rate, employer cost, step-by-step workings — which is valuable since there is no output schema. It does not discuss precision, rounding, or what happens for unsupported states.

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

Conciseness3/5

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

The purpose is front-loaded in the first clause, but the definition then runs as one dense sentence plus a long 'Covers:' inventory of brackets, credits, states and payroll programmes. The inventory establishes credibility but is poorly structured for scanning and displaces a short when-to-use/direction statement that would serve the agent better.

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 12-parameter, single-required-input calculator with no output schema, the description delivers the jurisdiction, tax year, input direction, response contents, and the full scope of what is and is not modelled. An agent has everything needed to decide this is the right tool and to call it with confidence.

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 description coverage is 100%, with enums and per-field notes for age, state, HSA limits and pre-tax deductions, so the schema carries the parameter burden. The description adds no field-level meaning beyond listing the tax areas covered (401(k) catch-up, section 125, state payroll programmes), so the baseline of 3 applies.

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

Purpose4/5

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

The opening clause states a specific verb+resource+input: take-home pay for a US employee computed from a gross yearly salary in USD under 2026 rules. The phrase 'from a gross yearly salary' implicitly separates it from the inverse sibling gross_for_target_net and from employer_cost, but no sibling is named explicitly, so the differentiation is inferential rather than stated.

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

Usage Guidelines3/5

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

Usage is implied by the input framing (gross-to-net, US jurisdiction, 2026 tax year), which lets an agent infer this is the wrong tool for a Netherlands comparison or for a target-net lookup. However there is no explicit when-to-use/when-not statement and no mention of the alternatives among the siblings, so the agent must reason it out.

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

All United States Salary Calculator 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.

Resources

Need Help?