Skip to main content
Glama
dma9527

irs-taxpayer-mcp

by dma9527

estimate_state_tax

Read-onlyIdempotent

Estimate state income tax for a state and tax year using a versioned calculation profile. Provide filing status and income to get the amount; unsupported state-year paths fail closed.

Instructions

Estimate state income tax using an explicit tax-year calculation profile. Unsupported state-year paths fail closed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taxYearYesTax year for the versioned state calculation profile
stateCodeYesTwo-letter state code
filingStatusNoFiling status (default: single)
taxableIncomeNoDeprecated alias for incomeBeforeStateDeductions
incomeBeforeStateDeductionsNoState income before the modeled state standard deduction and personal exemption

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
errorNo
isErrorYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.0.1
    • addedInput schema / properties / incomeBeforeStateDeductions
      Added value: +{
      +  "description": "State income before the modeled state standard deduction and personal exemption",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / taxYear
      Added value: +{
      +  "description": "Tax year for the versioned state calculation profile",
      +  "type": "integer"
      +}
    • changedInput schema / properties / taxableIncome / description
      Previous value: -"State taxable income (after state deductions)"New value: +"Deprecated alias for incomeBeforeStateDeductions"
    • changedInput schema / required
      Previous value: -[
      -  "stateCode",
      -  "taxableIncome"
      -]New value: +[
      +  "stateCode",
      +  "taxYear"
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "error": {
      +      "additionalProperties": false,
      +      "properties": {
      +        "code": {
      +          "type": "string"
      +        },
      +        "message": {
      +          "type": "string"
      +        },
      +        "suggestion": {
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "code",
      +        "message",
      +        "suggestion"
      +      ],
      +      "type": "object"
      +    },
      +    "isError": {
      +      "type": "boolean"
      +    },
      +    "text": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "text",
      +    "isError"
      +  ],
      +  "type": "object"
      +}
  2. First observedv0.5.3

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value beyond annotations by disclosing the fail-closed behavior ('Unsupported state-year paths fail closed') and the versioned-profile semantics, which tell the agent how errors and unsupported inputs are handled. No contradiction with annotations.

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?

Two sentences totaling roughly 20 words, with the core purpose first and the critical fail-closed behavior second. Every word earns its place; no 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?

With an output schema present, full parameter documentation in the schema, and robust annotations, the description does not need to cover return values or safety. The fail-closed disclosure fills the main behavioral gap; the only omission is explicit routing guidance versus closely related siblings, which is already penalized under usage guidelines.

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%, so the baseline is 3; the schema already documents taxYear, stateCode, filingStatus, the deprecated taxableIncome alias, and incomeBeforeStateDeductions. The description adds only the state-year path coupling, which is useful but does not substantially deepen parameter understanding beyond the schema.

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 description states a specific verb ('Estimate'), resource ('state income tax'), and a defining mechanism ('explicit tax-year calculation profile'). It clearly carves out state-level estimation, distinguishing it from siblings like calculate_federal_tax and get_state_tax_info by scope, though it does not name any sibling explicitly.

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?

The phrase 'using an explicit tax-year calculation profile' and the fail-closed note imply the tool is for supported state-year combinations where the caller provides a concrete tax year. However, there is no explicit when-to-use/when-not-to-use guidance or naming of alternatives (e.g., calculate_total_tax, get_state_tax_info), leaving selection largely to inference.

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