Skip to main content
Glama

State tax, NIIT and AMT estimate

state_tax_estimate
Read-onlyIdempotent

Estimate a household's 2026 federal income tax, net investment income tax (3.8%), alternative minimum tax and resident state income tax in one pass. States: CA, NY, PA, IL, OH, GA, NC, MI, TX, FL, NV, SD, WY, AK, TN, NH, WA (the ten most populous plus states without a wage income tax; Washington's capital gains tax included). Each state's figures carry the year they come from; every result says which rules were applied. Standard deductions only; local income taxes and most credits are not modeled.

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": {
      "filingStatus": "<filingStatus>"
    },
    "name": "state_tax_estimate"
  }
}

Input Schema

NameRequiredDescriptionDefault
agesNoAges of the filers at year-end (for senior deductions and state retirement exclusions).
stateNoTwo-letter state of residence (omit for federal only).
wagesNoWages, including RSU vests and NSO exercises.
isoSpreadNoBargain element of ISOs exercised and held at year-end (AMT preference).
otherIncomeNoInterest, Roth conversions and other ordinary income.
filingStatusYessingle or mfj (married filing jointly).
qualifiedIncomeNoQualified dividends plus net long-term capital gains.
retirementIncomeNoTaxable IRA and pension distributions.
netInvestmentIncomeNoNet investment income for NIIT (default qualifiedIncome).
taxableSocialSecurityNoTaxable part of Social Security benefits.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

The annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real behavioral context beyond that: data vintage ('each state's figures carry the year they come from'), rule provenance ('every result says which rules were applied'), the explicit 3.8% NIIT rate, Washington capital gains inclusion, and the modeling limitations (standard deductions only, no local taxes, most credits excluded). That is substantive disclosure for a pure-computation tool.

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?

Three sentences, front-loaded with the core capability before the state list and the caveats. The parenthetical about 'ten most populous plus states without a wage income tax' earns its place by explaining the otherwise arbitrary-looking enumeration. Slightly dense with parentheticals, but nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a ten-parameter, output-schema-less computation tool covering a complex tax domain, the description supplies the year, the jurisdictions, the taxes modeled, and the major modeling gaps. A reader can anticipate that results are broken out by jurisdiction with rule vintages. It leaves some ambiguity about household composition (no dependents parameter) and result shape, but overall it is sufficient to call the tool correctly.

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% and each of the ten parameters carries its own explanation (ages, isoSpread as AMT preference, qualifiedIncome, netInvestmentIncome defaulting to qualifiedIncome, and so on), so the schema does the heavy lifting. The description adds only indirect meaning, such as the state enumeration and what tax categories are folded in, without clarifying any individual parameter's format or interaction. 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?

The description names a specific verb (estimate) and enumerates the exact tax computations performed: 2026 federal income tax, 3.8% NIIT, AMT, and resident state income tax, all in one pass. No sibling tool in the provided list performs tax estimation, so the scope is unambiguous against retirement_plan, roth_conversion_plan, and similar planning tools.

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?

Coverage boundaries act as implicit when-to-use guidance: the state enum is spelled out and framed as 'the ten most populous plus states without a wage income tax,' telling the agent which jurisdictions this applies to and which it does not. The closing sentence ('Standard deductions only; local income taxes and most credits are not modeled') sets clear exclusions. It stops short of naming an alternative tool or a prerequisite condition, so it is not 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