Verifiable US tax oracle for AI agents: cited, machine-checkable federal and state tax computation
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.2/5 across 15 of 15 tools scored. Lowest: 3.3/5.
Each tool has a clearly distinct purpose: calculate_tax handles individuals, calculate_business_tax handles entities, calculate_fiduciary_tax handles estates/trusts, compute_return produces the complete federal return, compute_state_return handles state returns, and the remaining tools cover specific lookups (parameters, rules, facts, dependencies, cliffs, tipped occupations) or verification. Even with overlapping domains (explain_rule, lookup_tax_parameter, search_tax_rules, verify_fact, verify_tax_claim), their roles are sharply delineated.
Tool names follow a clear pattern: compute_return, compute_state_return, calculate_tax, calculate_business_tax, calculate_fiduciary_tax, determine_dependent, explain_rule, find_tax_cliffs, is_tipped_occupation, list_input_facts, lookup_tax_parameter, search_tax_rules, verify_fact, verify_tax_claim. Most use verb_noun (calculate_tax, lookup_tax_parameter, search_tax_rules, verify_fact). Minor deviations: compare_filing_statuses and compute_return use adjective/noun phrases rather than verb_noun, but they're still readable and follow the 'compute/calculate' theme.
15 tools is well-scoped for a comprehensive tax computation server. Each tool covers a distinct aspect of tax law (federal individual, business, fiduciary, state returns, dependency, rule lookup, parameter lookup, validation, cliff detection, fact verification, search). No tool feels redundant, and the count supports the ambitious scope without bloating.
The tool surface covers the full tax workflow: input discovery (list_input_facts), computation (calculate_tax, calculate_business_tax, calculate_fiduciary_tax, compute_return, compute_state_return), dependency determination (determine_dependent), rule/parameter lookup (explain_rule, lookup_tax_parameter, search_tax_rules), verification (verify_fact, verify_tax_claim), and specialized analysis (find_tax_cliffs, is_tipped_occupation, compare_filing_statuses). There's no obvious gap; the only potential missing feature is payroll tax computation, but that's outside the stated domain of income tax.
calculate_business_taxAInspectCompute US federal BUSINESS-ENTITY tax from the same cited corpus: check-the-box entity classification, Form 1120 corporate income tax (§ 179/168(k)/174A/163(j)/DRD/NOL, § 250, GBC/FTC/BEAT), S-corp entity taxes, corporate estimates, the § 4501 buyback excise, AET and PHC taxes. Individual returns → calculate_tax. Unknown keys are rejected; unmodeled territory refuses loudly with the reason.
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | REQUIRED for computation: the law-in-force date — use the intended tax year's year-end (e.g. "2025-12-31" for TY2025). Omitting it is an error, never a default. | |
| target | No | rule to derive (default: us.federal.corp.entity_level_income_tax — the classification-aware entity income tax). Other targets: us.federal.corp.entity_classification, .taxable_income, .income_tax_after_credits, .beat, .estimated.quarterly_payment, .stock_buyback_excise, .accumulated_earnings_tax, .phc_tax, .s_corp_entity_taxes | |
| corpNCTI | No | TY2025: the § 951A GILTI inclusion (with its § 78 gross-up); TY2026+: net CFC tested income (NCTI, OBBBA). The § 250 deduction applies 50% (2025) / 40% (2026+). The inclusion itself is GROSS INCOME (§ 951A(a)) — it must also be in corpGrossIncome with its § 78 gross-up; this fact drives only the § 250 deduction and FTC basket. The per-CFC tested-income aggregation is not modeled. In dollars. | |
| corpFDDEI | No | TY2025: foreign-derived intangible income (FDII); TY2026+: foreign-derived deduction eligible income (FDDEI, OBBBA — QBAI abolished). The § 250 deduction applies 37.5% (2025) / 33.34% (2026+). In dollars. | |
| corpPHCIncome | No | Personal holding company income (§ 543: dividends, interest, royalties, annuities, certain rents). In dollars. | |
| llcMemberCount | No | Number of members (owners) of the LLC — one member defaults to disregarded-entity treatment, two or more to partnership (Treas. Reg. § 301.7701-3(b)(1)). | |
| qreCurrentYear | No | Qualified research expenses for the current year (§ 41(b); § 41(d) qualification attested). In dollars. | |
| corpGrossIncome | No | The corporation's gross income (§ 61), INCLUDING any dividends received, any § 951 subpart F and § 951A NCTI/GILTI inclusions with their § 78 gross-ups (§ 951A(a) is a gross-income INCLUSION — the § 250 deduction is computed separately from corpNCTI), and any § 245A-eligible foreign-sub dividends. In dollars. | |
| corpIsREITorRIC | No | The corporation is a real estate investment trust (§ 856) or regulated investment company (§ 851). REFUSES — their dividends-paid deduction and distribution requirements are not modeled. | |
| entityLegalForm | No | The business's state-law legal form: a limited liability company, or a state-law corporation (a per-se corporation under Treas. Reg. § 301.7701-2(b)(1)). | |
| corpCapitalGains | No | The corporation's capital gains for the year (§ 1211(a): losses offset only these; net gain is ordinary-rate income for a corporation). In dollars. | |
| corpPriorYearTax | No | Tax shown on the corporation's preceding-year return (§ 6655(d) prior-year prong; unavailable if that year showed zero tax or was short). In dollars. | |
| corpCapitalLosses | No | The corporation's capital losses for the year, including prior-year § 1212(a) carryovers being used (allowed only to the extent of capital gains). In dollars. | |
| corpDividendsPaid | No | Dividends paid during the year (the § 561 dividends-paid deduction for the accumulated-earnings computation). In dollars. | |
| corpTaxableIncome | No | The C corporation's taxable income BEFORE the § 250 deduction, if already computed — used as-is when provided. Leave at 0 to have the engine compute it from corpGrossIncome and the deduction components (charitable/DRD/NOL machinery). CONTRACT: the § 250 deduction is computed separately from corpFDDEI/corpNCTI and subtracted by the tax rule — an AS-FILED Form 1120 line 30 already nets out § 250, so when providing corpFDDEI/corpNCTI enter the pre-§ 250 amount here (line 30 plus the § 250 deduction as filed), never the net. In dollars. | |
| qreAvgPrior3Years | No | Average annual qualified research expenses over the 3 preceding years — 0 means no prior QREs (the 6% startup rate of § 41(c)(4)(B) applies). In dollars. | |
| corpSection179Cost | No | Cost of § 179 property the corporation elects to expense — including qualified real property (roofs, HVAC, fire/security systems on nonresidential real property, § 179(d)(1)(B)(ii)) that § 168(k) cannot reach. Must NOT also be in corpEquipmentPurchases; EXCLUDE passenger automobiles and sport utility vehicles (the § 280F caps and the § 179(b)(5) SUV cap are not modeled). In dollars. | |
| corpStockIssuedFMV | No | Fair market value of stock issued by the corporation during the taxable year (including to employees) — netted against repurchases under § 4501(c)(3). In dollars. | |
| sCorpGrossReceipts | No | The S corporation's gross receipts for the year (§ 1375). In dollars. | |
| corpFiscalYearFiler | No | The corporation uses a FISCAL taxable year (or files a § 443 short-period return). Fiscal and short years are not modeled — the OBBBA parameters (§ 250 rates, § 59A 10.5%, § 960(d) 90%, § 448(c) $32M, the § 170(b)(2) 1% floor) apply by the taxable year's BEGINNING date, and § 443(b) annualization / § 15 proration are not encoded. | |
| corpForeignResearch | No | FOREIGN research or experimental expenditures paid this year — capitalized and amortized over 15 years (§ 174; first-year deduction is 1/30 under the midpoint convention). In dollars. | |
| corpNOLCarryforward | No | Net operating loss carryforward available this year (§ 172: deduction limited to 80% of taxable income before the NOL; post-TCJA, no carrybacks). In dollars. | |
| employeeAnnualWages | No | One employee's annual wages, for the employer-side payroll-tax target (§ 3111 FICA + FUTA). In dollars. | |
| corpDomesticResearch | No | Domestic research or experimental expenditures — currently deductible under § 174A (OBBBA, permanent from 2025). In dollars. | |
| corpDrdOwnershipTier | No | Ownership of the dividend-paying corporation: under 20% (50% DRD), 20–80% (65% DRD), or 80%+ affiliated (100% DRD, § 243(a)(3)). | |
| corpForeignTaxesNCTI | No | Foreign taxes attributable to the § 951A basket (GILTI/NCTI) — the § 960(d) deemed-paid credit takes the 80% (2025) / 90% (2026+, OBBBA) allowance, no carryovers. In dollars. | |
| corpTIThrough3Months | No | Corporate taxable income for the first 3 months (§ 6655(e) annualization, installments 1-2). In dollars. | |
| corpTIThrough6Months | No | Corporate taxable income for the first 6 months (§ 6655(e) annualization, installment 3). In dollars. | |
| corpTIThrough9Months | No | Corporate taxable income for the first 9 months (§ 6655(e) annualization, installment 4). In dollars. | |
| corpDividendsReceived | No | Dividends received from other taxable domestic corporations (§ 243 DRD; must also be included in corpGrossIncome). Enter only dividends on stock meeting the § 246(c) holding period (held more than 45 days during the 91-day window around the ex-dividend date; 90/181 for certain preferred) — attested; § 1059 extraordinary-dividend basis reduction not modeled. In dollars. | |
| sCorpNetPassiveIncome | No | Passive investment income net of directly-connected deductions (§ 1375(b)(2)). In dollars. | |
| sCorpShareholderCount | No | Number of shareholders, counting married couples and § 1361(c)(1) family members as one (§ 1361(b)(1)(A): may not exceed 100). | |
| sCorpTaxableIncomeAsC | No | The S corporation's taxable income computed as if it were a C corporation (§§ 1374(b)(1)/1375(b)(1)(B) cap). In dollars. | |
| corpBaseErosionTestMet | No | The corporation's base erosion percentage is 3% or more (2% for banks/securities dealers) — one of the two § 59A applicable-taxpayer tests. BEAT applies only to $500M+ multinationals. | |
| corpEquipmentPurchases | No | Cost of qualified § 168(k) property acquired AND placed in service this year (acquired after January 19, 2025 — 100% bonus depreciation, OBBBA-permanent). EXCLUDE passenger automobiles (the § 280F luxury-auto caps are not modeled) and anything entered in corpSection179Cost. In dollars. | |
| corpIsLargeCorporation | No | The corporation had taxable income of $1,000,000 or more in any of the 3 preceding taxable years (§ 6655(g)(2) 'large corporation' — may not use the prior-year safe harbor). | |
| corpOrdinaryDeductions | No | Ordinary business deductions (salaries, rents, prior-year amortization, …) — everything EXCEPT charitable contributions, the dividends-received deduction, and NOLs, which have their own limited rules. Enter compensation already limited by § 162(m) (no deduction for a covered employee's remuneration over $1,000,000 at a publicly held corporation — not modeled, attested). In dollars. | |
| corpOwnedByFiveOrFewer | No | More than 50% of the stock's value was owned (directly or via § 544 attribution) by 5 or fewer individuals during the last half of the year (§ 542(a)(2)). | |
| filedForm2553SElection | No | The entity filed a timely Form 2553 S election under § 1362(a)(1) (for an eligible entity this also deems association classification, Reg. § 301.7701-3(c)(1)(v)(C)). | |
| generalBusinessCredits | No | Aggregate current-year § 38(b) general business credits (e.g. the § 41 research credit target's result) — limited under § 38(c). In dollars. | |
| corpAvgGrossReceipts3yr | No | 3-year-average annual gross receipts (§ 448(c) test: $31M for 2025, $32M for 2026 — at or below it the § 163(j) limit does not apply). In dollars. | |
| corpForeignTaxesGeneral | No | Creditable foreign income taxes in the § 904(d) GENERAL basket. In dollars. | |
| corpStockRepurchasedFMV | No | Fair market value of the corporation's own stock repurchased (§ 317(b) redemptions and economically similar transactions) during the taxable year, for the § 4501 excise. In dollars. | |
| corpIsCoveredCorporation | No | The corporation is a 'covered corporation' for the § 4501 stock-repurchase excise tax: a domestic corporation whose stock is traded on an established securities market (§ 4501(b)). | |
| corpSection245ADividends | No | Foreign-source portion of dividends received from specified 10-percent-owned foreign corporations, eligible for the § 245A participation-exemption DRD (100%). Must also be included in corpGrossIncome. Attested by entry: US-shareholder status, NOT a § 245A(e) hybrid dividend, and the § 246(c)(5) 365-day holding period met; no foreign tax credit is allowed for the deducted portion (§ 245A(d)) — keep these taxes out of the FTC inputs. In dollars. | |
| sCorpHasAccumulatedEandP | No | The S corporation has accumulated earnings and profits from C-corporation years at the close of the year (§ 1375 applies only then). | |
| corpAccumulatedEandPStart | No | Accumulated earnings and profits at the close of the PRECEDING year (§ 535(c)(2) minimum-credit offset). In dollars. | |
| corpIsPersonalServiceCorp | No | The corporation's principal function is services in health, law, engineering, architecture, accounting, actuarial science, performing arts, or consulting (§ 535(c)(2)(B): $150,000 minimum credit instead of $250,000). | |
| filedForm8832CorpElection | No | The entity filed a Form 8832 election to be classified as an association taxable as a corporation (Treas. Reg. § 301.7701-3(c)). | |
| corpBaseErosionTaxBenefits | No | Base erosion tax benefits for the year (§ 59A(c)(2)) — include the base-erosion percentage of any NOL deduction (§ 59A(c)(1)(B)). Added back to reach modified taxable income. In dollars. | |
| corpUndistributedPHCIncome | No | Undistributed personal holding company income (§ 545: taxable income adjusted, less federal taxes and the dividends-paid deduction). In dollars. | |
| sCorpRecognizedBuiltInGain | No | Net recognized built-in gain during the § 1374(d)(7) 5-year recognition period after a C-to-S conversion (0 if the period has passed or there was no conversion). In dollars. | |
| corpBusinessInterestExpense | No | Business interest expense (§ 163(j): limited to 30% of EBITDA-based ATI unless the § 448(c) gross-receipts test is met). In dollars. | |
| corpCharitableContributions | No | The corporation's charitable contributions — current-year gifts plus allowable prior-year § 170(d)(2) carryovers being used (both subject to the same ceiling and, from 2026, the OBBBA floor). In dollars. | |
| corpFilesConsolidatedReturn | No | The corporation joins a consolidated return (§§ 1501-1504) — intercompany eliminations and SRLY rules are not modeled, so this refuses. | |
| corpReasonableNeedsRetention | No | Earnings retained for the reasonable needs of the business (§§ 535(c)(1), 537 — documented needs; part of the accumulated earnings credit). In dollars. | |
| sCorpHasMultipleStockClasses | No | The corporation has more than one class of stock (§ 1361(b)(1)(D); differences in voting rights alone do not create a second class, § 1361(c)(4)). | |
| sCorpPassiveInvestmentIncome | No | The S corporation's passive investment income — royalties, rents, dividends, interest, annuities (§ 1375(b)(3)). In dollars. | |
| sCorpHasIneligibleShareholder | No | Any shareholder is ineligible under § 1361(b)(1)(B)–(C): a nonresident alien, or an entity other than an estate or eligible trust/exempt organization. | |
| corpForeignSourceIncomeGeneral | No | Foreign-source taxable income in the general basket (§ 904 limitation numerator; § 861 expense allocation attested). In dollars. | |
| corpAdjustedOrdinaryGrossIncome | No | Adjusted ordinary gross income (§ 543(b)(2)) — the 60% test base. In dollars. | |
| corpPortfolioDebtFinancedPercent | No | Average indebtedness percentage (0-100) of debt-financed portfolio stock (§ 246A) — reduces the 50%/65% DRD proportionally; 0 = not debt-financed. | |
| corpAvgAdjustedFinancialStatementIncome | No | 3-year-average adjusted financial statement income (§ 56A) — over $1 billion triggers the corporate AMT, which this engine refuses to approximate. In dollars. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full responsibility for behavioral transparency. It mentions error behavior ('Unknown keys are rejected; unmodeled territory refuses loudly with the reason'), which is helpful. However, it does not explicitly state that the tool is read-only or has no side effects, though 'compute' strongly implies it. A clear statement about safety would push to 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single paragraph that efficiently conveys the core purpose, scope, and error handling. It is front-loaded with the main action. A slight improvement would be breaking into multiple sentences for readability, but it remains clear and reasonably concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 63 parameters and no output schema, the description covers the tool's domain and error handling well but omits any indication of the output format or return value. For a complex tool, including what the user gets back (e.g., a tax computation result) would enhance completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 description text does not add any parameter-specific details beyond what the schema already provides. It only describes overall tool behavior, so no extra value for parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's specific purpose: 'Compute US federal BUSINESS-ENTITY tax' and lists numerous explicit tax provisions. It directly distinguishes itself from the sibling tool 'calculate_tax' by noting that individual returns should use that tool, providing clear differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance: 'Individual returns → calculate_tax' tells the agent when not to use this tool. It also implies that business entities are the intended scope. This direct instruction helps avoid misapplication.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
calculate_fiduciary_taxAInspectCompute US federal income tax for an ESTATE or TRUST (Form 1041): the § 1(e) compressed brackets and § 642(b) exemption. Input is taxable income before the exemption, after the §§ 651/661 distribution deduction. Retained capital gains refuse loudly (§ 1(h) trust breakpoints not modeled). Grantor trusts belong on the grantor's individual return via calculate_tax.
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | REQUIRED for computation: the law-in-force date — use the intended tax year's year-end (e.g. "2025-12-31" for TY2025). Omitting it is an error, never a default. | |
| target | No | rule to derive (default: us.federal.fiduciary.income_tax). | |
| fiduciaryType | No | Form 1041 filer type for the § 642(b) exemption: estate ($600), simple trust required to distribute all income currently ($300), or complex trust ($100). Grantor trusts do not file their own tax — use the grantor's individual return. | |
| fiduciaryLongTermGains | No | Net long-term capital gain retained by the estate/trust. Any positive amount REFUSES — the § 1(h) preferential breakpoints for estates and trusts are not modeled. In dollars. | |
| fiduciaryIncomeBeforeExemption | No | The estate/trust's taxable income BEFORE the § 642(b) exemption but AFTER the §§ 651/661 income-distribution deduction (the DNI machinery is attested by this input). In dollars. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses key behaviors: retained capital gains cause an error, omitting asOf is an error, and §1(h) breakpoints are not modeled. It also explains the computation assumptions (income before exemption, after DNI deduction). This is excellent transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at 5 sentences, front-loads the core purpose, and every sentence adds essential information. No redundant or filler content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters, no nested objects, and no output schema, the description covers the computation context, input requirements, limitations, and alternative tools. It is complete enough for an AI agent to correctly select and invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds meaningful context beyond schema: it explains the meaning of each parameter in the tax computation (e.g., fiduciaryIncomeBeforeExemption is after distribution deduction, fiduciaryLongTermGains cause refusal). It also provides the exemption amounts for each fiduciaryType, which are absent from schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it computes US federal income tax for estates and trusts (Form 1041) using specific code sections, and distinguishes from sibling tools by explicitly noting that grantor trusts should use calculate_tax. The verb 'compute' and resource 'US federal income tax for estate/trust' are specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear when-to-use context: for estates and trusts, and explicitly excludes grantor trusts with an alternative tool name (calculate_tax). It also warns that retained capital gains will cause an error. However, it does not explicitly list all situations where the tool should not be used.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
calculate_taxAInspectCompute US federal INDIVIDUAL income tax (or balance due if withholding is given) from a content-addressed corpus of cited rules. NEVER estimate tax yourself — call this, and report ONLY numbers returned by oracle calls made with the real facts (never hand-check or approximate a line the oracle can compute: your recalled parameters may be stale). Negative result = refund. Returns the answer, every assumption made, and hashes that let anyone re-verify the full derivation offline. Facts are grouped (filing, income, retirement, credits, …) — fill the groups that apply; unknown keys are rejected, and the engine names any missing fact the target needs. When source documents CONFLICT on a value, do not silently pick one: compute both branches, disclose the conflict and your choice; an interview/confirmation answer (rollover, conversion, taxable-amount screens) usually reflects taxpayer intent better than a payer form's box code — prefer it and disclose. That heuristic covers FACTS only: LEGAL classifications (qualifying child vs other dependent, filing status, SSTB) follow the statute's tests, not intake checkbox labels — a generic 'claim dependent credit' flag does not convert a qualifying child into an ODC dependent. TRANSCRIBE documented amounts as given even when they look anomalous (e.g. state withholding in a no-income-tax state): disclose the anomaly, never delete or 'correct' a documented number from outside knowledge. If you believe an oracle result is wrong, report the ORACLE's number and note your dissent — never substitute your own: the corpus is primary-source-verified and your recollection is not. Business entities → calculate_business_tax; estates/trusts → calculate_fiduciary_tax; § 152 dependency → determine_dependent.
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | REQUIRED for computation: the law-in-force date — use the intended tax year's year-end (e.g. "2025-12-31" for TY2025). Omitting it is an error, never a default. | |
| state | No | state taxable income for the state tax targets (us.ca/us.va/us.il/us.ny/us.oh/us.nc/us.ga/us.md/us.mo/us.wi/us.mn income_tax; parameters via lookup_tax_parameter) | |
| filing | No | who is filing: status, age/blindness, dependency, student status | |
| income | No | wages, interest, capital gains, unemployment, foreign earned income | |
| target | No | rule to derive (default: net tax; balance due when payments_estimates.federalTaxWithheld is given). Determinations: us.federal.eligible.tips_deduction, us.federal.estimated.quarterly_payment, us.federal.estimated.safe_harbor_met | |
| credits | No | CTC/ODC counts, dependent care, saver's, adoption, education | |
| itemized | No | Schedule A: SALT, mortgage, medical, charitable | |
| documents | No | RAW document transcription (preferred over hand-mapped facts): W-2 boxes, 1099-R boxes/codes, SSA-1099 boxes, dependents' birth dates. SSA-1099s are first-class: box 5 sums into socialSecurityBenefits and box 6 into withholding, so the § 86 taxable-benefits worksheet runs on the transcribed total instead of a hand-mapped guess. The tool derives wages/withholding (incl. Form 8959 Part IV), box-3/5 wage coordination, dependent classifications, age facts, and early-distribution penalties deterministically — and errors if the same value is also passed as a hand-mapped fact. | |
| kiddie_tax | No | Form 8615 inputs for a child subject to § 1(g) | |
| retirement | No | social security, IRA/pension distributions, early-distribution penalty | |
| adjustments | No | IRA/HSA contributions, student-loan and car-loan interest | |
| investor_amt | No | AMT preferences (ISO spread) and § 1202 QSBS exclusion | |
| tips_overtime | No | § 224 tips and § 225 overtime deductions (OBBBA) | |
| healthcare_ptc | No | § 36B premium tax credit / Form 1095-A reconciliation | |
| rentals_passive | No | Schedule E rentals/royalties + § 469 passive-loss netting (Form 8582 via us.federal.passive_loss_allowed) | |
| self_employment | No | Schedule C / K-1, QBI inputs, SE deductions, home office | |
| household_employer | No | Schedule H nanny/household-employee taxes | |
| payments_estimates | No | withholding, prior-year safe harbor, annualized installments |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description fully discloses the tool's behavior: it will never hand-check computations, always report oracle-called numbers, disclose conflicts and assumptions, and refuse to 'correct' documented amounts. It also explains the heuristic for preference given to interview answers over box codes. This is exemplary transparency for an agent-facing tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense and long but every sentence carries functional value: scope, constraints, conflict handling, transcription rules, and routing. It is not redundant; it packs a lot of essential guidance into a single block, though it could be slightly more streamlined.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the input schema (nested objects, many parameters), the description provides strong context on overall behavior, returns (answer + assumptions + hashes), and edge-case handling (conflicts, anomalies, missing facts). It does not detail output structure (no output schema available) but covers the essential operational context adequately.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides per-parameter descriptions covering 100% of parameters, so the description adds little beyond the schema. The description's global instructions (e.g., never estimate, transcription rules) apply across parameters but do not per-parameter clarify meaning or usage beyond what the schema states.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool computes US federal individual income tax (or balance due) using a cited-rule corpus, which clearly identifies its purpose and distinguishes it from sibling tools like calculate_business_tax and calculate_fiduciary_tax.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit when-to-use guidance, including 'Business entities → calculate_business_tax; estates/trusts → calculate_fiduciary_tax; § 152 dependency → determine_dependent' and instructs never to estimate tax, instead always calling this tool with real facts. It also outlines conflict-resolution behavior, which is crucial for correct usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
compare_filing_statusesAInspectCompute the answer under every filing status for the same facts — e.g. to answer 'should we file jointly or separately?'. Statuses that need more facts report their error instead of guessing.
| Name | Required | Description | Default |
|---|---|---|---|
| facts | Yes | facts for the computation: either flat corpus fact ids (see list_input_facts) or the same group objects calculate_tax accepts (filing, income, retirement, …), plus optional target and asOf. Business/fiduciary/dependent facts are accepted flat. Unknown keys are rejected by name — nothing is ever silently dropped. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool computes for all statuses, returns errors for incomplete facts, and rejects unknown keys (from schema description). It does not explicitly state that the operation is read-only, but the context implies no side effects. Overall, good disclosure for a compute tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero filler. The first sentence states the core purpose, and the second clarifies error handling. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple parameter and no output schema, the description is sufficient for an agent to understand the tool's function. It covers purpose, error behavior, and parameter flexibility. Minor omission: no mention of the return format (e.g., a map of status to result/error), but overall complete for its complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a full description of the 'facts' parameter. The tool description adds extra context, noting that facts can be flat corpus IDs or group objects (like filing, income, retirement) accepted by calculate_tax, and that business/fiduciary/dependent facts are accepted flat. This enriches the schema description, earning a slightly higher score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool computes answers under every filing status for the same facts, with an explicit example ('should we file jointly or separately?'). This directly distinguishes it from sibling tools like calculate_tax, which likely process a single status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear use case (comparing statuses) and explains that statuses with insufficient facts report errors rather than guessing. However, it does not explicitly state when not to use the tool or mention alternatives, which would further guide selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
compute_returnAInspectCompute the COMPLETE Form 1040 bottom-line set in one call — the 17 lines that determine the return (1a, 9, 10, 11, 12e, 15, 16, 17 AMT, 19, 22, 23, 24, 25d, 27a, 28, 32, 33, 34/37), each whole-dollar rounded by the engine. Takes the SAME input as calculate_tax (prefer the documents block: transcribe W-2/1099-R/SSA-1099 boxes and dependent birth dates — SSA-1099s are first-class, box 5 and box 6 are summed for you; the tool derives ages, classifications, Part IV withholding, and penalties deterministically). Never assemble return lines by hand — this tool is the return. TRANSCRIPTION CONVENTIONS: (1) a PRIOR-YEAR Form 1040 in the file supplies CONTINUING conditions the current-year interview omits — the 'Someone can claim: You as a dependent' checkbox and the blindness boxes carry forward unless the current-year data contradicts them; (2) COMMUNITY PROPERTY: do NOT split income 50/50 between MFS spouses when they lived apart all year with no transfers (§ 66(a) allocates earned income to the earner) or when a written separation agreement ended the community — transcribe each document to its named earner; never invent a Form 8958 split the intake does not request; (3) bonus depreciation for assets placed in service 1/1-1/19/2025 is 40% (§ 168(k) pre-OBBBA phase-down; 100% only for property ACQUIRED after 1/19/2025).
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | REQUIRED for computation: the law-in-force date — use the intended tax year's year-end (e.g. "2025-12-31" for TY2025). Omitting it is an error, never a default. | |
| state | No | state taxable income for the state tax targets (us.ca/us.va/us.il/us.ny/us.oh/us.nc/us.ga/us.md/us.mo/us.wi/us.mn income_tax; parameters via lookup_tax_parameter) | |
| filing | No | who is filing: status, age/blindness, dependency, student status | |
| income | No | wages, interest, capital gains, unemployment, foreign earned income | |
| target | No | rule to derive (default: net tax; balance due when payments_estimates.federalTaxWithheld is given). Determinations: us.federal.eligible.tips_deduction, us.federal.estimated.quarterly_payment, us.federal.estimated.safe_harbor_met | |
| credits | No | CTC/ODC counts, dependent care, saver's, adoption, education | |
| itemized | No | Schedule A: SALT, mortgage, medical, charitable | |
| documents | No | RAW document transcription (preferred over hand-mapped facts): W-2 boxes, 1099-R boxes/codes, SSA-1099 boxes, dependents' birth dates. SSA-1099s are first-class: box 5 sums into socialSecurityBenefits and box 6 into withholding, so the § 86 taxable-benefits worksheet runs on the transcribed total instead of a hand-mapped guess. The tool derives wages/withholding (incl. Form 8959 Part IV), box-3/5 wage coordination, dependent classifications, age facts, and early-distribution penalties deterministically — and errors if the same value is also passed as a hand-mapped fact. | |
| kiddie_tax | No | Form 8615 inputs for a child subject to § 1(g) | |
| retirement | No | social security, IRA/pension distributions, early-distribution penalty | |
| adjustments | No | IRA/HSA contributions, student-loan and car-loan interest | |
| investor_amt | No | AMT preferences (ISO spread) and § 1202 QSBS exclusion | |
| tips_overtime | No | § 224 tips and § 225 overtime deductions (OBBBA) | |
| healthcare_ptc | No | § 36B premium tax credit / Form 1095-A reconciliation | |
| rentals_passive | No | Schedule E rentals/royalties + § 469 passive-loss netting (Form 8582 via us.federal.passive_loss_allowed) | |
| self_employment | No | Schedule C / K-1, QBI inputs, SE deductions, home office | |
| household_employer | No | Schedule H nanny/household-employee taxes | |
| payments_estimates | No | withholding, prior-year safe harbor, annualized installments |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden and delivers: whole-dollar rounding, deterministic derivation of 'ages, classifications, Part IV withholding, and penalties', first-class SSA-1099 summation, and a detailed TRANSCRIPTION CONVENTIONS section covering prior-year carry-forward conditions, § 66(a) community-property allocation, and § 168(k) bonus depreciation. It does not describe the output structure beyond the line list, but the derivation and input-handling behaviors are well disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense and purpose-front-loaded, but runs roughly 700 words. The TRANSCRIPTION CONVENTIONS block, while useful, mixes genuinely behavioral guidance (community-property rules, prior-year carry-forward) with a substantive depreciation-rate rule (§ 168(k) 40% vs 100%) that reads more like tax-law reference than a transcription instruction. It earns its sentences for the most part, but the depreciation tangent and verbose prose keep it from being tightly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the extreme complexity — 18 top-level parameters with deeply nested objects (state, filing, documents, self_employment, rentals_passive, etc.) and 100% schema coverage — the description appropriately focuses on the highest-value workflow guidance: computing all 17 return lines, preferring the documents transcription block, and the transcription conventions. No output schema exists, and the description names the output lines rather than describing their structure, a minor gap, but for a computation tool of this scale the coverage is strong.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with exhaustive per-parameter descriptions, so the baseline is 3, but the description adds genuine selection guidance: 'prefer the documents block' over hand-mapped facts, the requirement that asOf is 'REQUIRED for computation... Omitting it is an error, never a default', and the transcription conventions that tell the agent how to populate parameters (community-property no-split, SSA box summing, no invented Form 8958 splits). This adds workflow value beyond the schema's field-level documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb+resource: 'Compute the COMPLETE Form 1040 bottom-line set in one call' and enumerates the exact 17 lines (1a, 9, 10... 34/37), making the scope unambiguous. It distinguishes itself from calculate_tax by addressing input sharing ('Takes the SAME input as calculate_tax') and asserts its primacy ('Never assemble return lines by hand — this tool is the return'), clearly separating it from the federal compute siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear contextual guidance on input strategy ('prefer the documents block: transcribe W-2/1099-R/SSA-1099 boxes and dependent birth dates') and a firm directive against manual assembly. It references calculate_tax as sharing input, implying alternate compute paths, but does not explicitly state when to use this tool versus compute_state_return or calculate_business_tax, nor provide an explicit 'when not to use' exclusion list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
compute_state_returnAInspectCompose a STATE return's printed-form line set deterministically (2025 IL-1040 / VA 760 / CA 540 / NY IT-201 / PA-40 / NJ-1040 / OH IT 1040 / NC D-400 / GA 500 / MD 502 / MO-1040 / WI Form 1 / MN M1 / SC1040 / AL Form 40 / OR-40) — correct line NUMBERS from the printed forms and whole-dollar rounding, with the state tax computed by the oracle targets internally. NC and GA start from federalAGI: NC runs the AGI-tiered child deduction, the independent itemize-vs-standard selection, and the Bailey/military/SS auto-subtractions; GA FORCES itemizing for federal itemizers (pass gaFederalItemized), runs the per-spouse retirement exclusion and Low Income Credit targets, and caps total credits at the line 16 tax. PA is CLASS-BASED and NJ is CATEGORY-BASED: transcribe the pa*/nj* class-or-category fields (PA: Box 16 compensation, per-spouse loss classes; NJ: the line 15-26 category nets — a category loss is suppressed per the printed rule, and the composer runs the pension-exclusion, Worksheet H deduction-vs-credit, EITC/CTC/CDCC targets itself) — federalAGI is NOT the PA or NJ base. OH starts from federal AGI: pass federalAGI + ohBusinessIncome and the composer runs the Business Income Deduction, MAGI-tiered exemptions, and the Schedule of Credits ordering (retirement/senior/CDCC/exemption credits before the joint filing credit's line-11 base). Workflow: run compute_return first for the federal substrate, compute any state-specific components the citations describe (additions, subtractions, credits without targets — disclose each), then call this ONCE and report its line set VERBATIM. Never hand-assemble state line numbers: transposed lines on correct dollars are the dominant state error mode. ALWAYS pass taxableSocialSecurity and unemploymentCompensation when nonzero (VA/CA/NY subtractions are applied by the composer). ALWAYS transcribe the intake's state-specific block (e.g. ca_tax_return.ca_form540_schca: AB 5 employee-classification additions; va_sch_a fields; county/use-tax questions) — those fields drive composer inputs. For VA MFJ, pass vaYourVagi/vaSpouseVagi (the separate-VAGI worksheet) so the composer can run the Spouse Tax Adjustment worksheet itself. For MD, pass mdSubdivision (the mandatory county tax — line 28), mdEicQualifyingChild for the 50%/100%/45% EIC routing, and mdNetCapitalGainSubject from an agent-completed Form 502CG when FAGI exceeds $350,000; the composer runs the pension-exclusion, exemption-chart, CTC, poverty-credit, and local EIC/poverty worksheets itself. Maryland part-year returns (Form 502 line 12 proration) are not composed. For MO, split each income item per spouse (moFagiYou/moFagiSpouse etc. — Missouri combined returns compute a SEPARATE chart tax per spouse), pass the line 9/10 federal-tax amounts per the printed lists, and remember the NEW TY2025 100% capital-gains subtraction (moCapitalGainYou/Spouse); Kansas City/St. Louis 1% earnings taxes are separate city returns the composer does not produce. For WI, pass wiScheduleIAdjustments (IRC frozen at 12/31/2022 — post-2022 federal changes convert on Schedule I), wiCapitalGainSubtraction from Schedule WD (30%/60% LTCG exclusion), and note the Act 15 SB-16 retirement subtraction FORFEITS every credit — the composer enforces the forfeiture; compute both ways before electing it. For MN, remember the IRC is frozen at May 1, 2023 (2025 OBBBA items convert on Schedule M1NC → mnAdditions/mnSubtractions), pass mnSsAlternativeMethod when AGI exceeds the SS threshold (the composer takes the greater), mnAmt whenever M1MT preferences exist, and mnNetInvestmentIncome for the 1% NIIT; M1C/M1REF credit schedules are transcribed buckets. For SC, the base is FEDERAL TAXABLE INCOME — pass scFederalTaxableIncome (Form 1040 line 15 verbatim; a negative amount is preserved via subtraction line r), NOT federalAGI; pass scNetLtcgAfterLosses for the 44% LTCG deduction (net LT gains against ALL capital losses first), the per-person retirement/military/age-65 fields (military retirement is 100% deductible and REDUCES the same person's other two deductions — the composer handles the interplay), and federalEITC (the composer adds the 125% NONREFUNDABLE SC EITC into line 13 itself — never also put it in nonrefundableCredits); the 2025 state-tax addback for federal itemizers goes in scAdditions. For AL, the composer builds Alabama AGI from transcribed lines (alWages = W-2 Box 16, alOtherIncome, alTaxableRetirement* for the Schedule RS 65+ $6,000 exclusion — still $6,000 in 2026, HB388 died) — federalAGI is NOT the base; pass alFederalTaxPlusNiit (1040 line 22 + Form 8960) and alFederalRefundableCredits (EIC+ACTC+AOC+adoption+2439) for the UNLIMITED line 12 federal tax deduction, and remember overtime earned Jan-Jun 2025 is exempt and already out of Box 16. For OR, pass the federal-tax-worksheet components (orFederal1040Line22, orFederalPtc from 8962 line 24, orFederalAoc/orFederalRefundableAdoption — the EITC/ACTC are NOT subtracted) for the AGI-capped line 10 subtraction, taxableSocialSecurity (subtracted in full), or2024TaxLiability for the 9.863% kicker, and the Kids Credit inputs (orKidsUnder6 + addbacks); OBBBA tips/overtime/vehicle-interest are CLAIMED for Oregon via OR-ASC codes 390/391/392 in orSubtractions but added back for the Kids Credit test.
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | Yes | year-end date, e.g. 2025-12-31 — REQUIRED | |
| caAmt | No | OVERRIDE for Form 540 line 61 — prefer caIsoPreference + caAmtTaxesAddback so the composer builds Schedule P AMTI and evaluates us.ca.amt itself; a passed caAmt wins. | |
| mnAmt | No | M1 line 11: Schedule M1MT alternative minimum tax (6.75% broadened base, agent-computed — REQUIRED whenever AMT preference items exist; disclose) | |
| njSrp | No | NJ-1040 line 53c Shared Responsibility Payment (Worksheet L/Schedule NJ-HCC, hand-computed from coverage months; composer zeroes it below the filing threshold) | |
| wages | No | federal line 1a wages (NY IT-201 line 1) | |
| caBhst | No | us.ca.bhst result (pass the oracle target's answer) — Form 540 line 62 Behavioral Health Services Tax (R&TC § 17043, 1% of CA taxable income over $1,000,000); added into line 64 total tax when nonzero. | |
| caYCTC | No | us.ca.yctc result (pass the oracle target's answer) | |
| useTax | No | consumer use / sales-use tax owed on the return | |
| alWages | No | Form 40 line 5b: W-2 BOX 16 state wages from ALL states (Schedule W-2 col I+J; Alabama state wages often EXCEED federal Box 1 — deferrals are AL-taxable). Overtime earned Jan 1-Jun 30, 2025 is exempt and already EXCLUDED from Box 16 (W-2 Box 14 'EX OT WAGES'). Falls back to the shared wages input. | |
| njWages | No | NJ-1040 line 15: W-2 BOX 16 state wages total (falls back to the shared wages input; NJ taxes cafeteria/125 benefits and some items federal Box 1 excludes) | |
| additions | No | total state additions to federal AGI (e.g. NY 414(h) A-104 + IRC-125 A-101; VA Schedule ADJ line 2 codes). GATE RULE: coded addition/subtraction line-item arrays sitting under a false 'do you have additions/subtractions' boolean are inactive template rows (especially $1-$4 placeholder amounts) — transcribe $0 for them and disclose; the gate controls for these arrays | |
| alIs65You | No | primary taxpayer was 65 or older — enables their $6,000 retirement exclusion (NOTE: still $6,000 for 2026; the reported $12,000 increase was HB388, which died May 2025) | |
| caCalEITC | No | us.ca.caleitc result (pass the oracle target's answer) | |
| filingHoh | No | ||
| moFagiYou | No | MO-1040 line 1Y: the PRIMARY taxpayer's share of federal AGI — Missouri combined returns SPLIT total FAGI between spouses per the AGI worksheet (each spouse's own income; joint items allocated). Defaults to the full federalAGI when omitted (one-income couple). | |
| njPension | No | NJ-1040 line 20a TAXABLE pension/annuity/IRA distributions (NJ three-year rule / general rule basis recovery already applied; Social Security and Railroad Retirement are exempt and never entered) | |
| orPenalty | No | OR-40 line 43: penalty AND interest for filing or paying late (one combined printed line — 5% late-pay penalty, +20% over 3 months late, 100% for 3 consecutive unfiled years, plus the late-payment interest) | |
| scIs65You | No | primary taxpayer was 65 or older by December 31 — raises the retirement cap to $10,000 and enables the $15,000 age-65 deduction (line q-1, reduced by the retirement + military deductions claimed) | |
| dependents | No | dependent count (CA dependent exemption credits; NY $1,000 exemptions) | |
| exemptions | No | personal + dependent exemption COUNT (self + spouse + dependents) | |
| federalAGI | No | federal Form 1040 line 11 (from compute_return, verbatim). REQUIRED for il/va/ca/ny/or — the composer refuses without it. NOT used by PA (class-based: pass the pa* class fields instead). | |
| mdMw506nrs | No | MD line 42: tax withheld on Form MW506NRS (nonresident real property sale) | |
| mnItemized | No | Schedule M1SA Minnesota itemized deductions AFTER M1SA's own 3%/10%/80% limitation — the composer takes the larger of this or the computed standard deduction (MFS: standard barred when the spouse itemizes; pass mnMfsSpouseItemizes) | |
| mnStdBoxes | No | 65-or-older (born before January 2, 1961) and blind boxes for you/spouse — each adds $2,000 (single/HOH) or $1,550 (married statuses) to the standard deduction | |
| njExcessDi | No | NJ-1040 line 60 excess disability insurance withheld (over $380.42; NJ-2450) | |
| njRentPaid | No | rent paid on the NJ principal residence (tenants) — the composer enters 18% of it on line 40a | |
| njScorpNet | No | NJ-1040 line 22 net pro rata share of S corporation income (NJ-K-1; negative suppressed) | |
| orInterest | No | OR-40 line 44: interest on UNDERPAYMENT OF ESTIMATED TAX from Form OR-10 (boxes 44a/44b) — late-payment interest goes in line 43 instead | |
| orStdBoxes | No | OR-40 boxes 17a-d: count of 65-or-older (born before January 2, 1961... turned 65 by January 1, 2026) and blind boxes for you/spouse — each adds $1,200 (single/HOH) or $1,000 (other statuses) to the standard deduction | |
| paGambling | No | PA-40 line 8: gambling and lottery winnings net of wager costs (noncash PA Lottery prizes exempt; cash prizes taxable) | |
| paInterest | No | PA-40 line 2: PA-taxable interest (gross class — no expenses; includes commercial-annuity interest taxable as PA interest) | |
| vaYourVagi | No | PRIMARY taxpayer's separate VAGI (MFJ only — the 760 instructions' 'Worksheet for Determining Separate Virginia Adjusted Gross Income': own wages/SE/pensions, own share of joint items 50/50, own age deduction and subtractions). Enables the composer's Spouse Tax Adjustment worksheet (Form 760 line 17). vaYourVagi + vaSpouseVagi must equal line 9 VAGI. | |
| alDonations | No | Form 40 line 34: Schedule DC donation check-offs total (reduces the refund) | |
| alPenalties | No | Form 40 line 31: Schedule ATP Part II penalties (estimated-tax penalty Form 2210AL etc.) — added to an amount owed, or SUBTRACTED from the refund per the printed line 35 formula | |
| federalEITC | No | federal EIC, line 27a (from compute_return) | |
| filingJoint | No | ||
| mdItemizing | No | taxpayer itemized FEDERALLY and elects Maryland itemized deductions — the composer computes 17a−17b−17c (with the H.B. 352 7.5% phase-out over $200,000/$100,000-MFS FAGI) and still takes the standard deduction if larger (Maryland allows either) | |
| mnAdditions | No | M1 line 2: Schedule M1M line 10 + M1MB line 9 additions (non-MN municipal bond interest, federal bonus-depreciation/§ 179 addbacks, positive M1NC adjustments — Minnesota's IRC is frozen at May 1, 2023, so 2025 OBBBA items convert on Schedule M1NC) | |
| moItemizing | No | taxpayer itemized FEDERALLY and wants Missouri itemized deductions — the composer computes MO-A Part 2 (federal itemized + payroll-tax addback − net state income taxes) and takes the LARGER of that or the standard deduction unless moRequiredToItemize | |
| njArcherMsa | No | Archer MSA contributions (federal Form 8853; NJ has NO HSA deduction — never enter HSA amounts) | |
| njCojCredit | No | NJ-1040 line 44 credit for income taxes paid to other jurisdictions (Schedule NJ-COJ, hand-computed; composer caps at the line 43 tax). NO credit for Pennsylvania-reciprocal WAGES (the PA/NJ agreement) — Philadelphia wage tax DOES qualify. | |
| njDividends | No | NJ-1040 line 17 dividends | |
| njExcessFli | No | NJ-1040 line 61 excess family leave insurance withheld (over $545.82; NJ-2450) | |
| njWwcCredit | No | NJ-1040 line 62 Wounded Warrior Caregivers Credit (Schedule NJ-WWC; gross income ≤ $100,000 MFJ/HOH/QSS, ≤ $50,000 single/MFS) | |
| orAdditions | No | OR-40 line 8: Schedule OR-ASC line A5 additions (non-Oregon municipal interest, federal-state depreciation differences, 529 recapture) | |
| paDividends | No | PA-40 line 3: PA-taxable dividends INCLUDING mutual-fund capital-gain distributions (PA classifies them as dividends, not gains) | |
| scAdditions | No | SC1040 line 2 total additions (lines a-e: the state income/sales tax deducted in federal itemized deductions MUST be added back on line a; out-of-state rental/business losses; non-SC municipal bond interest; expenses on reserve/subsistence income). CRITICAL for TY2025: SC REJECTED OBBBA conformity (IRC conformity frozen at December 31, 2024) — line e must ADD BACK every OBBBA deduction in federal taxable income (tips exclusion, overtime premium, the $6,000 senior deduction, car-loan interest, OBBBA business items). | |
| vaItemizing | No | taxpayer itemized federally (VA requires the same election, Va. Code § 58.1-322.03(1)) — enables the VA Schedule A computation from the component inputs below; Form 760 line 10 replaces the line 11 standard deduction | |
| wiDonations | No | Form 1 line 24: Schedule 3 fund donations total | |
| alDependents | No | Form 40 line 14 dependent count — Alabama's OWN relationship list (§ 40-18-19: child/stepchild/parent/grandparent/sibling/in-laws/blood uncle-aunt-nephew-niece with over-50% support; NOT federal § 152) — $1,000/$500/$300 each by AL AGI (us.al.dependent_exemption); falls back to the shared dependents input | |
| alIs65Spouse | No | spouse was 65 or older — enables their own $6,000 exclusion | |
| filingStatus | No | REQUIRED in practice: the federal filing status — drives the state bracket schedule, standard deduction column, and exemption structure. The filingJoint/filingHoh/filingHohOrQss booleans are legacy aliases; when filingStatus is present it wins. | |
| gaLic65Count | No | Low Income Credit Worksheet line 3: 1 if filer or spouse is 65+, 2 if both | |
| gaUetPenalty | No | Form 500 line 42: Form 500 UET estimated tax penalty | |
| jurisdiction | Yes | ||
| mdPensionYou | No | primary taxpayer's qualifying § 401(a)/403/457(b) pension in FAGI for the Worksheet 13A pension exclusion — ONLY if 65+/totally disabled (or spouse totally disabled); IRAs/SEP/Keogh never qualify. The composer evaluates us.md.pension_exclusion per spouse. | |
| mnDependents | No | dependents on Schedule M1DQC — $5,200 each (2025), phased 2% per $2,500 ceil-step of AGI over $358,550 MFJ/QSS, $239,050 single, $298,800 HOH, $179,275 MFS (gone once the excess passes $122,500/$61,250-MFS); $0 for dependent-claimed filers | |
| mo529Deposit | No | MO-1040 line 52: refund deposited to a Missouri 529 (MOST) account (minimum $25, Form 5632) | |
| moFagiSpouse | No | MO-1040 line 1S: the spouse's share of federal AGI (combined returns). 1Y + 1S must equal the federal AGI. A NEGATIVE share triggers the 12 CSR 10-2.710 zeroing the composer applies (negative spouse $0, other spouse the netted joint FAGI; both $0 when combined FAGI is negative). | |
| moNrPayments | No | MO-1040 lines 39+40: MO-2NR/MO-2ENT nonresident partner/entertainer payments | |
| ncCharitable | No | NC Schedule A: IRC § 170 charitable contributions allowed for the year (no NC dollar cap) | |
| ncTaxCredits | No | D-400 line 16: D-400TC total (other-state credit worksheet, historic rehab) — hand-computed; the composer caps at the line 15 tax. NC has NO EITC and NO child/dependent care credit. | |
| njBaitCredit | No | NJ-1040 line 63 pass-through Business Alternative Income Tax credit (PTE-K-1) | |
| njBlindCount | No | line 8 count (0-2): filer/spouse blind or disabled — $1,000 each | |
| orFederalAoc | No | American Opportunity Credit (1040 line 29) — subtracted in the federal tax worksheet | |
| orFederalPtc | No | premium tax credit from Form 8962 LINE 24 (the full allowable credit regardless of advance payments) — subtracted. NOTE: the EITC and additional child tax credit are NOT subtracted. | |
| orKidsUnder6 | No | dependents age 5 or younger at the end of 2025 (max 5 count) — $1,050 each Oregon Kids Credit (us.or.kids_credit, refundable, MFS denied). A child claimed only via a RELEASED dependent exemption does not count. | |
| scDependents | No | SC line w dependent count (must equal the federal return's) — $4,930 each for 2025 (us.sc.dependent_exemption); falls back to the shared dependents input | |
| scIs65Spouse | No | spouse was 65 or older by December 31 (lines p-2/q-2) | |
| scLumpSumTax | No | SC1040 line 7: tax on lump-sum distribution (SC4972, agent-computed, attached) | |
| subtractions | No | total state subtractions OTHER than the automatic ones (taxable social security / unemployment have their own inputs below; e.g. NY S-136 alimony paid, IL retirement subtraction) | |
| vaFamilyVagi | No | Schedule ADJ line 10 total family VAGI (you + spouse + dependents' VAGI) for the Credit for Low-Income Individuals poverty test; defaults to line 9 VAGI when omitted | |
| vaSpouseVagi | No | spouse's separate VAGI for the STA worksheet (Form 760 line 17 box; MFJ only) | |
| wi2441Credit | No | Schedule WI-2441 line 14 — Wisconsin's additional child and dependent care credit (its own recomputation; transcribe the schedule's result) | |
| wiAge65Boxes | No | count of 65-or-older boxes (taxpayer/spouse) — $250 each on line 10b (Wisconsin has no blindness exemption; the $700 line 10a exemptions come from the shared `exemptions` count) | |
| wiMarriedHoh | No | the Form 1 'Head of household, married' checkbox applies — shares the MFS $150 school property tax credit cap | |
| alAdjustments | No | Form 40 line 9 / Part II total (per-spouse IRA deduction, Keogh/SEP, early-withdrawal penalty, alimony paid, adoption expenses, MOVING EXPENSES (Alabama kept them), SE health insurance, College Counts 529/PACT, small-employer health premiums, wind/flood retrofit, catastrophe savings, HSA, First/Second-Chance Home Buyer, firefighter insurance, ABLE) | |
| alOtherIncome | No | Form 40 Part I lines 1-3 and 5-7 total EXCLUDING retirement (alimony received, business income/loss, gains — the 1/1/2025+ precious-metal-bullion gain is EXEMPT, rents/royalties/partnerships, farm; negative allowed). Retirement goes in the alTaxableRetirement* fields for the Schedule RS exclusion. | |
| gaNolUtilized | No | Form 500 line 15b: Georgia NOL utilized (Schedule 4; cannot exceed line 15a or the 80% limitation — composer caps at 15a) | |
| ilK12Expenses | No | IL qualified K-12 education expenses (before the $250 floor) | |
| md502crPartBB | No | MD line 31: local tax credit from Form 502CR Part BB line 1 | |
| mdCtcChildren | No | Maryland CTC qualified children (dependents under 6, or over 5 and under 17 with a disability) — the composer evaluates us.md.ctc ($500/child, phased out $50 per $1,000 of FAGI over $15,000, $0 above $24,000; refundable via 502CR Part CC into line 45) | |
| mdSubdivision | No | REQUIRED for MD: the taxing county where the filer resided on the LAST day of the tax year (Form 502 political-subdivision box) — one of baltimore_city, allegany, anne_arundel, baltimore_county, calvert, caroline, carroll, cecil, charles, dorchester, frederick, garrett, harford, howard, kent, montgomery, prince_georges, queen_annes, st_marys, somerset, talbot, washington, wicomico, worcester, nonresident. Drives the mandatory local tax (line 28: flat 2.25%-3.30%; Anne Arundel bracketed with its own printed table; Frederick tiered on the WHOLE income with real cliffs). | |
| mnStateRefund | No | M1 line 6: state income tax refund from federal Schedule 1 line 1 (its own subtraction line) | |
| moFederalTax9 | No | MO-1040 line 9 'Tax from federal return': federal 1040 line 22 MINUS lines 27a and 29, MINUS Schedule 2 Part 1 line 3, MINUS Schedule 3 Part 2 line 9 — never withholding; the EIC must be subtracted | |
| moSsExemptYou | No | the primary's MO-A Section C exemption: their TAXABLE Social Security/SSD (1040 line 6b share), 100% exempt — pass ONLY if 62+ by December 31 (the MO-1040 age box) or on Social Security Disability (attested) | |
| njAlimonyPaid | No | NJ-1040 line 32 court-ordered alimony PAID (still deductible for NJ; never child support) | |
| njBusinessNet | No | NJ-1040 line 18 net profits from business (Schedule NJ-BUS-1 Part I; negative allowed — the composer suppresses a net category loss per the printed rule) | |
| njFederalCdcc | No | the federal Form 2441 child and dependent care credit — enables the line 64 NJ CDCC (us.nj.cdcc: 50%→10% of it by NJ taxable income, $150,000 cap) | |
| njGamblingNet | No | NJ-1040 line 24 net gambling winnings (losses net WITHIN the category; NJ Lottery prizes of $10,000 or less are exempt) | |
| njMfsSameHome | No | MFS and both spouses maintained the SAME main home — halves the property-tax deduction cap ($7,500) and credit ($25) | |
| njNjclassPaid | No | NJ-1040 line 37b NJCLASS loan principal+interest paid (composer caps at $2,500) | |
| njOtherIncome | No | NJ-1040 line 26 other income | |
| njSeniorCount | No | line 7 count (0-2): filer/spouse 65 or older (born 1960 or earlier for TY2025) — $1,000 each | |
| njTuitionPaid | No | NJ-1040 line 37c NJ-institution tuition paid (composer caps at $10,000) | |
| ohEicOverride | No | OVERRIDE: us.oh.eic oracle answer — wins over the composer's 30%-of-federalEITC line 13 computation | |
| or529Deposits | No | OR-40 line 51: Oregon 529 deposits from Schedule OR-529 (reduce the refund) | |
| orPtePayments | No | OR-40 line 36: estimated payments from Schedule OR-K-1 line 20 (PTE owner payments via Form OR-19) | |
| orStateRefund | No | OR-40 line 12: OREGON state income tax refund from federal Schedule 1 line 1 (never other states' or local refunds) | |
| paBusinessNet | No | PA-40 line 4, TAXPAYER's own net business/profession/farm income or LOSS (negative allowed; within-class netting of the taxpayer's own activities only — a loss never crosses classes or spouses) | |
| paEstateTrust | No | PA-40 line 7: estate/trust income (PA Schedule J; an estate or trust cannot distribute a loss — never negative) | |
| paPropertyNet | No | PA-40 line 5, taxpayer's own net gain/loss from sale/exchange/disposition of property (negative allowed; no carryover) | |
| caHsaDeduction | No | federal HSA deduction (Form 8889 line 13) — California does not conform to § 223: the composer ADDS it back for CA | |
| filingHohOrQss | No | ||
| gaIndCrCredits | No | Form 500 line 20: IND-CR Summary total OTHER than the CDCC (the composer adds us.ga.cdcc itself from gaFederalCdccAllowed) | |
| ilChildUnder12 | No | IL CTC gate: a QUALIFYING CHILD (§ 152(c) lineage — child/stepchild/foster/sibling or their descendants) under age 12. A qualifying-relative/ODC-only dependent does NOT satisfy this even if under 12; leave false. | |
| ilEitcOverride | No | us.il.eitc oracle target's answer (35 ILCS 5/212(a)(vi), (b-5), (b-10): 20% of the federal EITC recomputed WITHOUT the § 32(c)(1)(A)(ii) childless age gate) — WINS over the generic 20%-of-federalEITC line-29 computation when present. MUST be used (not merely optional) for a taxpayer age 18-24 or 65+ with NO qualifying children: federalEITC alone is correctly $0 for that population under federal law, so line 29 = 20% x federalEITC would wrongly zero out Illinois' decoupled credit — pass us.il.eitc's computed answer instead. Safe to pass for every IL EITC claimant (agrees with the generic computation outside the decoupled population). | |
| mdEarnedIncome | No | MD line 1b earned income (wages + net SE profit, no loss netting) — the poverty level credit base (us.md.poverty_level_credit) and the local poverty credit (19C) | |
| mdStateRefunds | No | MD line 8: taxable state/local income tax refunds included in federal AGI (subtraction) | |
| mnSubtractions | No | M1 line 7 subtractions (M1M line 40 + M1MB line 22) EXCLUDING the composer-computed Social Security subtraction: U.S. government interest, K-12 education expenses, charitable over $500 for non-itemizers (50% of the excess), bonus-depreciation recovery, M1R age-65+/disabled, M1QPEN public pension, military items, the new 2025 items (coerced debt, consumer enforcement, foreign service, SEIU stipends) | |
| moAdditionsYou | No | MO-A Part 1 line 7Y: the primary's additions (non-Missouri state/local bond interest, PTE/NOL addbacks, nonqualified 529/ABLE distributions, food pantry, nonresident property tax) | |
| moLtcDeduction | No | MO-1040 line 16: qualified long-term care insurance premiums (12+ month policies, net of federally deducted amounts, per the worksheet) | |
| njEitcOverride | No | OVERRIDE: us.nj.eitc oracle answer — wins over the composer's 40%-of-federalEITC / $260 computation | |
| njHezDeduction | No | NJ-1040 line 34 Health Enterprise Zone deduction (TB-56) | |
| njVeteranCount | No | line 9 count (0-2): filer/spouse honorably-discharged veterans — $6,000 each | |
| ohAge65OrOlder | No | filer (or spouse) was 65 or older at year end — $50 senior citizen credit (once per return; NOT available if the lump sum distribution credit was ever taken) | |
| orKickerDonate | No | filer elects to donate the ENTIRE kicker to the State School Fund (irrevocable after the due date) — line 32 becomes $0 and box 55 is checked | |
| orSubtractions | No | OR-40 line 13: Schedule OR-ASC line B7 subtractions — including the OBBBA-conforming tips/overtime/passenger-vehicle-interest deductions (codes 390/391/392: Oregon lets you claim the same amounts as federal), US government interest, the federal pension percentage subtraction, OR-HOME first-time home buyer savings, tier 2 Railroad Retirement. Do NOT include Social Security (automatic via taxableSocialSecurity). | |
| scCareChildren | No | count of qualifying care children/dependents — 2+ raises the SC CDCC cap from $210 to $420 | |
| scCareExpenses | No | federal Form 2441 child/dependent care EXPENSES (not the credit) — SC line 11 pays 7%, max $210/$420 (us.sc.cdcc); DENIED to married filing separately | |
| scI290Payments | No | SC1040 line 19: nonresident real estate withholding paid on Form I-290 | |
| vaAgeDeduction | No | OVERRIDE ONLY — pass vaAgeQualifyingFull/vaAgeQualifyingTested instead and the composer computes the age deduction itself (including the AFAGI social-security exclusion agents routinely miss). When splitting an odd joint total between spouses (Form 760 lines 4a/4b), the odd dollar goes to the SPOUSE. | |
| ageOrBlindBoxes | No | count of age-65+/blind boxes checked (taxpayer/spouse, per box) | |
| alAtpOtherTaxes | No | Schedule ATP Part I taxes OTHER than the use tax (which uses the shared useTax input): catastrophe-savings recapture (+2.5%), etc. | |
| caIsoPreference | No | ISO exercise spread AMT preference (§ 56(b)(3) as modified by R&TC § 17062) — with caAmtTaxesAddback this lets the composer BUILD Schedule P AMTI itself (AMTI = line 19 taxable income + taxes deducted in the CA itemized deduction + this preference; standard deduction added back instead when not itemizing) and evaluate us.ca.amt internally; caAmt (a precomputed answer) wins if both are given | |
| caRentersCredit | No | us.ca.renters_credit result (pass the oracle target's answer) — nonrefundable, joins the exemption credits in the line-48 subtraction from tax. | |
| cityWithholding | No | NY line 73 NYC withholding | |
| gaExclusionTier | No | primary taxpayer's GA retirement-exclusion tier: 62-64 during any part of the year or permanently/totally disabled ($35,000 cap) vs 65+ ($65,000 cap) (us.ga.retirement_exclusion) | |
| gaLicExemptions | No | Low Income Credit Worksheet line 2: self + spouse + natural/legally adopted children (never other dependents or unborn) (us.ga.low_income_credit) | |
| mdContributions | No | MD lines 35-39: voluntary fund contributions total (reduces the refund) | |
| mdHouseholdSize | No | persons in the family/household from the federal return — enables the poverty level credit computation (2025 guideline $15,650 + $5,500 each additional person) | |
| mdPensionSpouse | No | spouse's qualifying pension for their own 13A column (same gates) | |
| mdRangerPension | No | MD line 10b: Retired Forest/Park/Wildlife Ranger pension exclusion (Worksheet 13E, agent-computed, disclosed) | |
| mnOtherTaxes14a | No | M1 line 14a: M1HOME/M1529 recapture, M1LS lump-sum tax, and the Schedule NIIT amount if computed outside the composer | |
| mnRrTier1Offset | No | Tier 1 Railroad Retirement benefits already subtracted on M1M line 17 — the SS worksheet (steps 25-29) reduces the simplified-method subtraction by this amount (no double subtraction) | |
| moHcsmDeduction | No | MO-1040 line 17: health care sharing ministry contributions not deducted federally | |
| moOtherTaxesYou | No | MO-1040 line 34Y: 10% of the Federal Form 4972 lump-sum distribution tax, and/or recapture of the low income housing credit (Form 8611) — the printed checkboxes. (Form 4970 trust accumulation amounts are a SUBTRACTION, not a line 34 tax.) | |
| ncScorpPayments | No | D-400 line 21d: NC tax paid by an S corporation on the filer's behalf | |
| njExcessUiWfSwf | No | NJ-1040 line 59 excess UI/WF/SWF withheld (two+ employers over $184.02; Form NJ-2450) | |
| scContributions | No | SC1040 line 28: check-off contributions total (I-330 attached; reduces the refund) | |
| scLatePenalties | No | SC1040 line 32: late filing/late payment penalties and interest | |
| scTuitionCredit | No | SC1040 line 21: REFUNDABLE tuition tax credit (Form I-319: 50% of qualifying SC-institution tuition within the form's limits — agent-computed with disclosure, form attached) | |
| vaItemizedOther | No | VA Sch A other itemized deductions | |
| wiBothSpouses67 | No | both spouses 67+ on December 31 (joint returns) — raises the SB-16 cap to $48,000 | |
| extensionPayment | No | payment made with an extension request. VA 760 line 22 (its own line, never folded into the estimated-payments line). NY IT-201 line 75 is the COMBINED line — 'estimated tax payments and amount paid with Form IT-370' — so for NY this is added into the same line as estimatedPayments, not kept separate. | |
| gaDependentCount | No | Form 500 line 7c total dependents (7a qualified + 7b unborn-with-heartbeat; never self/spouse) — $4,000 each (us.ga.dependent_exemption) | |
| moCapitalGainYou | No | the primary's share of federally reported capital gains (Form 1040 line 7a) — the composer subtracts 100% (MO-A line 18, H.B. 594, NEW for TY2025; a negative amount enters as $0) | |
| moSsExemptSpouse | No | the spouse's Section C SS/SSD exemption on the same gates | |
| ncUseTaxEstimate | No | use the printed no-receipts consumer use tax table (keyed to line 14 taxable income, us.nc.use_tax) instead of the useTax input | |
| njAbcaAdjustment | No | NJ-1040 line 35 Alternative Business Calculation Adjustment (Schedule NJ-BUS-2 line 11 — the only cross-category loss softener, 20-year carryforward) | |
| njChildrenUnder6 | No | count of line 10/11 dependents age 5 or younger on 12/31 (born 2020 or later for TY2025) — the line 65 NJ Child Tax Credit multiplier ($1,000→$200 each by taxable income ≤ $80,000; MFS ineligible) | |
| njDispositionNet | No | NJ-1040 line 19 net gains from disposition of property (Schedule NJ-DOP; NO capital-gain preference, NO loss carryover; negative allowed — suppressed) | |
| njGoldStarCredit | No | NJ-1040 line 47 Gold Star Family Counseling Credit (hours × TRICARE rate) | |
| njPartnershipNet | No | NJ-1040 line 21 distributive share of partnership income (NJK-1; negative suppressed) | |
| njRentRoyaltyNet | No | NJ-1040 line 23 net rents/royalties/patents/copyrights (negative suppressed) | |
| nycTaxableIncome | No | NYC taxable income (IT-201 line 47) if NYC resident | |
| ohBusinessIncome | No | OH Schedule of Business Income Part 1 line 10: total business income (Schedule B/C/D/E/F + guaranteed payments to 20%+ owners + § 4797) — the composer runs the $250,000/$125,000 Business Income Deduction and the flat-3% line 6/8b arithmetic from it | |
| ohResidentCredit | No | OH Schedule of Credits line 39 resident credit for taxes paid other states (Ohio IT RC, hand-computed) | |
| orSpouseItemizes | No | MFS only: the other spouse itemizes — the Oregon standard deduction becomes $0 | |
| orYoungestUnder3 | No | the youngest dependent was younger than 3 at year end — raises the Oregon EIC from 9% to 12% of the federal EITC (us.or.eic) | |
| paRentRoyaltyNet | No | PA-40 line 6, taxpayer's own net rents/royalties/patents/copyrights (short-term rentals under 30 days are BUSINESS income, line 4) | |
| paResidentCredit | No | PA-40 line 22: resident credit for tax paid other states (Schedule G-L; not for reciprocal-state compensation: IN/MD/NJ/OH/VA/WV). Subtracts BEFORE Tax Forgiveness — the composer handles the ordering. | |
| scActiveTradeTax | No | SC1040 line 8: I-335 flat 3% tax on active trade or business income (agent-computed; the electing income must also appear in scSubtractionsOther as the line l subtraction) | |
| scCatastropheTax | No | SC1040 line 9: tax on excess Catastrophe Savings Account withdrawals | |
| stateWithholding | No | state income tax withheld (IL line 25 / VA 19a / CA 71 / NY 72). CONVENTIONS: IL line 25 sums state withholding from EVERY document (W-2s + all 1099s). NY line 72 = W-2 box 17 NYS withholding PLUS NY-coded state withholding from 1099s whose PAYER has an in-state (NY) address; NY-coded withholding printed by an OUT-OF-STATE-addressed payer is NOT included; disclose any excluded amount in notes. VA 19a = the PRIMARY taxpayer's withholding from EVERY document type (W-2, 1099, VK-1 — Form 760 line 19 instructions name all three; the payer's address does NOT matter for VA, unlike NY); a jointly-issued document's state withholding splits 50/50 between 19a/19b with the odd dollar to the primary. | |
| vaRefundableEitc | No | OVERRIDE ONLY — the composer now computes the Form 760 line 23 credit itself from federalEITC + the eligibility inputs below. If passed, this refundable amount wins over the computed selection. | |
| wiFarmlandCredit | No | Form 1 line 31: farmland preservation credit (Schedules FC/FC-A, transcribed) | |
| wiOtherPenalties | No | Form 1 line 26 other penalties (see instructions p.25) | |
| wiVeteransCredit | No | Form 1 line 34: eligible veterans and surviving spouses property tax credit | |
| yonkersSurcharge | No | us.ny.yonkers_surcharge result (pass the oracle target's answer) — 16.75% of the Yonkers worksheet's netted base (nyYonkersBase). Added into line 62's total and printed on its own line (IT-201 LINE 55, not 54 — line 54 is MCTMT) when nonzero. | |
| caAmtTaxesAddback | No | taxes actually included in the CA itemized deduction (property taxes etc. surviving the Schedule CA SALT adjustments) — the Schedule P line 2 addback used when the composer builds AMTI from caIsoPreference; $0 when not itemizing (the composer adds back the standard deduction instead) | |
| estimatedPayments | No | state estimated payments ONLY (extension payments and prior-year credited overpayments have their own lines where the form provides them) | |
| gaFederalItemized | No | Form 500 line 12a: federal Schedule A total. Supplying this FORCES Georgia itemizing ('Leave Line 11 blank if you itemize deductions on your Federal return') — a federal standard-deduction filer must omit it. | |
| ilPropertyTaxPaid | No | IL property tax on principal residence, net of business-use portion | |
| ilTeacherExpenses | No | IL Schedule 1299-C educator materials expenses | |
| mdBusinessCredits | No | MD line 25: business tax credits (Form 500CR — e-file only; transcribed) | |
| mdFederalItemized | No | MD line 17a: total federal itemized deductions (federal Schedule A line 17) | |
| mdInterestCharges | No | MD line 51: Form 502UP interest / late-filing interest | |
| mdSsRrBenefitsYou | No | primary taxpayer's TOTAL Social Security + Railroad Retirement benefits (taxable or not) — reduces the $41,200 cap in the primary's 13A column | |
| mnPenaltyInterest | No | M1 line 28: late-filing/late-payment penalty and interest (agent-computed per the instructions) | |
| moAdditionsSpouse | No | MO-A Part 1 line 7S: the spouse's additions | |
| moFederalItemized | No | MO-A Part 2 line 1: total federal itemized deductions (federal Schedule A total) plus any approved cultural contributions (literary/musical/scholastic/artistic donations, § 143.141) | |
| moOtherDeductions | No | MO-1040 lines 21-24 bucket: beginning farmer, transport facility, foster parent deductions (agent-transcribed) | |
| moSubtractionsYou | No | MO-A subtractions for the primary EXCLUDING the composer-computed capital gain (line 18) and business income deduction (line 17): exempt federal-obligation interest, state refund, military retirement (100%), railroad retirement, 529/ABLE contributions ($8,000/taxpayer), qualified health insurance premiums, depreciation adjustments, agriculture disaster relief | |
| ncMedicalExpenses | No | NC Schedule A line 7a: medical/dental expenses BEFORE the floor — the composer subtracts 7.5% of federal AGI | |
| ncRealEstateTaxes | No | NC Schedule A: real estate property taxes (NC allows NO income/sales tax deduction) — inside the $20,000 combined cap | |
| njAlimonyReceived | No | NJ-1040 line 25 alimony received (NJ did not adopt the TCJA repeal — still NJ income) | |
| njDomesticPartner | No | registered NJ domestic partner claimed as a line 6 regular exemption (+$1,000) | |
| njMedicalExpenses | No | unreimbursed medical expenses (Worksheet F line 1) — the composer applies the 2%-of-line-29 floor | |
| njPensionEligible | No | line 28a gate: filer (or spouse if joint) was 62+ OR blind/disabled per Social Security guidelines on the last day of the year — enables the pension exclusion (us.nj.pension_exclusion) | |
| njTaxableInterest | No | NJ-1040 line 16a taxable interest (NJ-exempt: federal obligations, NJ municipal bonds — exclude here, report on 16b) | |
| nyHouseholdCredit | No | NYS household credit from table 2 (us.ny.parameters citation) | |
| ohInterestPenalty | No | IT 1040 line 11 interest penalty on underpayment of estimated tax (Ohio IT/SD 2210) | |
| orKidsLossAddback | No | Kids Credit worksheet Part B: federal losses + OR-ASC loss-subtraction codes beyond the $20,000 allowance, plus ALL excluded foreign earned income — added back to qualifying income | |
| paNrk1Withholding | No | PA-40 line 17: nonresident tax withheld from PA Schedule(s) NRK-1 | |
| refundableCredits | No | state refundable credits, e.g. the NY credit block: ESCC + NYS EIC + IT-216 + NYC EIC + NYC school tax + NYC child care (WITHOUT their own oracle target, self-computed per the us.ny.parameters citation and disclosed) PLUS us.ny.it214 (the Real Property Tax Credit, which DOES have an oracle target as of TY2025 v5 — pass its computed answer here, not a hand-derived percentage of rent) | |
| scSubsistenceDays | No | SC line s: days as a full-time federal/state/local law enforcement officer, firefighter, or EMS worker — $16/day subsistence allowance | |
| vaItemizedMedical | No | VA Sch A line 1: total medical/dental expenses BEFORE any floor (VA applies its own 10%-of-FAGI floor — Virginia deconforms from the federal 7.5% floor) | |
| wiFederalEicForWi | No | the federal EIC AS COMPUTED UNDER WISCONSIN'S IRC (Schedule I Part III recomputation when Part I adjustments exist) — defaults to the shared federalEITC when omitted | |
| wiHomesteadCredit | No | Form 1 line 33: homestead credit (Schedule H/H-EZ circuit breaker, agent-computed, refundable) | |
| wiRepaymentCredit | No | Form 1 line 32: repayment of income previously taxed credit | |
| alCampaignCheckoff | No | Form 40 line 20: $1/$2 Alabama Democratic/Republican party checkoffs — these ADD to the tax due (not fund-neutral like the federal checkoff) | |
| claimedAsDependent | No | someone else can claim this taxpayer as a dependent (carry the prior-year 1040 'Someone can claim: You as a dependent' checkbox forward as a continuing condition unless the current-year interview contradicts it). IL: zeroes the line 10 exemption allowance when base income exceeds the exemption amount. VA: limits the standard deduction to earned income. | |
| gaOtherStateCredit | No | Form 500 line 18: other state(s) tax credit (printed worksheet, hand-computed; other-state return copy required) | |
| gaOtherWithholding | No | Form 500 line 25: GA tax withheld on G2-A / G2-FL / G2-LP / G2-RP statements (never W-2/1099 amounts — those go in the shared stateWithholding for line 24) | |
| gaRetirementIncome | No | primary taxpayer's UNEARNED retirement income for the exclusion (pensions, interest, dividends, net rents, capital gains, royalties, military retirement; joint property at 50%; NEVER Social Security — that subtracts automatically) | |
| mdHomebuyerPenalty | No | MD line 51a: first-time homebuyer savings account 10% withdrawal penalty | |
| mdRecapturedCredit | No | MD line 21a: recaptured credit from Form 502CR Part DD line 1 | |
| moOtherTaxesSpouse | No | MO-1040 line 34S | |
| moPublicPensionYou | No | the primary's PUBLIC-source pension (federal/state/local government, 1040 line 5b share) — the composer runs MO-A Part 3 Section A (min(pension, $47,633) less their Section C exemption). Military retirement goes in moSubtractionsYou instead (100%, MO-A line 10). | |
| ncBaileyRetirement | No | NC Schedule S line 20: Bailey settlement retirement benefits (NC/local government or US government incl. military retirees with 5+ years of creditable service as of Aug 12, 1989; state 401(k)/457 contributed before that date) — fully deducted; enclose the 1099-R | |
| ncMortgageInterest | No | NC Schedule A: qualified mortgage interest — the composer applies the $20,000 combined cap with real estate taxes and takes itemized only when it beats the standard deduction | |
| njEitcAgeDecoupled | No | flat-$260 NJEITC attested: 18+, no qualifying child, met all federal EIC requirements except age, not claimed as a dependent (NJ eliminated both federal age limits) | |
| njSpecialExclusion | No | line 28b Special Exclusion attested: filer (and spouse if joint) will NEVER be eligible for Social Security/Railroad Retirement because the employer did not participate — adds $6,000 (MFJ/HOH/QSS) / $3,000 (single/MFS) | |
| nycHouseholdCredit | No | NYC household credit from table 5 | |
| ohRetirementIncome | No | retirement income received on account of retirement still INCLUDED in Ohio AGI, both spouses combined (NOT Social Security/railroad/uniformed-services amounts — those are deducted and never qualify) — drives the retirement income credit (max $200) | |
| or2024TaxLiability | No | the filer's 2024 total Oregon personal income tax liability (after the other-state credit, before all other credits/payments — 2024 OR-40 line 24 tax-before-credits MINUS the Schedule OR-ASC code 802/815 credit for taxes paid to another state, per Table 8 / Kicker worksheet Part A) — the composer computes the 9.863% kicker (us.or.kicker). Requires the 2024 return filed before the 2025 return. Prorate by 2024 Oregon-AGI share if the filing status changed (worksheet Parts B/C). | |
| orCreditRecaptures | No | OR-40 line 22: tax recaptures from Schedule OR-ASC line C5 | |
| orKidsObbbaAddback | No | Kids Credit worksheet line 2: tips/overtime/vehicle-interest subtractions claimed (OR-ASC codes 390/391/392) — ADDED BACK to qualifying income | |
| pa529Contributions | No | Schedule O code T: § 529 contributions, ALREADY capped at $19,000 per beneficiary per taxpayer-spouse (2025); no deduction for rollovers/beneficiary changes | |
| paScheduleDcCredit | No | PA-40 line 23 component: the Child and Dependent Care Enhancement credit — pass us.pa.cdcc's computed answer (= 100% of the federal Form 2441 line 9a tentative credit; refundable) | |
| scDependentsUnder6 | No | SC line t: dependents under age 6 on December 31 — the SAME $4,930 again each (on top of their line w exemption) | |
| scOtherWithholding | No | SC1040 line 20: other SC withholding from 1099s (W-2 amounts go in the shared stateWithholding for line 16) | |
| vaItemizedCasualty | No | VA Sch A casualty/theft losses (protected from the overall limitation) | |
| vaItemizedGambling | No | VA Sch A gambling losses (§ 165(d), limited to winnings; protected from the overall limitation) | |
| wiOtherStateCredit | No | Form 1 line 20: net income tax paid to another state (Schedule OS, agent-computed) | |
| wiRentHeatIncluded | No | 2025 rent on the principal Wisconsin residence with heat INCLUDED (line 16a; 2.4% via the printed table's $100-row midpoints) | |
| yonkersWithholding | No | NY line 74 Yonkers withholding (W-2 box 19 with a Yonkers locality) | |
| alAppliedToNextYear | No | Form 40 line 33: overpayment applied to 2026 estimated tax | |
| alInterestDividends | No | Form 40 line 6: interest and dividend income (Schedule B attached if over $1,500) | |
| gaMilitaryExclusion | No | GA military retirement exclusion for under-62 retirees (Schedule 1 page 3 worksheet: $17,500 + additional $17,500 when GA earned income exceeds $17,500 — hand-computed, per qualifying spouse) | |
| mdChildCareExpenses | No | MD line 9: child and dependent care EXPENSES from federal Form 2441 line 6 — an income subtraction in Maryland (separate from any 502CR Part B credit); the composer caps it at $3,000 ($6,000 when mdChildCareTwoOrMoreDependents) | |
| mnAppliedToNextYear | No | M1 line 30: refund applied to 2026 estimated tax | |
| mnMfsSpouseItemizes | No | MFS only: the other spouse claims Minnesota itemized deductions — bars the standard deduction (the composer then requires mnItemized) | |
| moAppliedToNextYear | No | MO-1040 line 50: overpayment applied to 2026 estimated tax | |
| moBusinessIncomeYou | No | the primary's MISSOURI-SOURCE net business income per the p.16 worksheet (Schedule C line 31 + Schedule E line 32 + Schedule F/4835 profits, losses netted, MINUS agricultural disaster relief payments already on MO-A line 16; $0 if net loss) — the composer takes the 20% § 143.022 deduction (MO-A line 17Y) | |
| moCapitalGainSpouse | No | the spouse's share of federal capital gains for the 100% subtraction | |
| moEnterpriseZoneYou | No | MO-1040 line 28Y: enterprise zone / rural empowerment zone income modification | |
| moOtherFederalTax10 | No | MO-1040 line 10 'Other federal tax': Schedule 2 Part 1 line 3 + Part 2 lines 8/14/15 + recapture in line 21 + Schedule 3 Part 1 line 1 (attach 4255/8611/8828 for recapture) | |
| moPayrollTaxAddback | No | MO-A Part 2 lines 2-7 total: the 2025 employee Social Security tax (capped $10,918 per spouse), Railroad Retirement Tier I+II (capped $17,327 per spouse, net of employer refunds), Medicare tax (with Form 8959 adjustments), and self-employment tax (Schedule 2 line 4 − Schedule 1 line 15 + Form 8959 line 13) — Missouri ADDS payroll taxes into itemized deductions | |
| moPrivatePensionYou | No | the primary's PRIVATE-source taxable pension/annuity/IRA/401(k) (1040 lines 4b+5b share) — Section B caps each spouse at $6,000 and phases out by income | |
| moPropertyTaxCredit | No | MO-1040 line 43: Form MO-PTS property tax credit (refundable circuit breaker — actual property tax up to $1,100 owners / 20%-of-rent up to $750 renters, from the printed chart; net household income gates $30,000 owners / $27,200 renters; agent-computed from MO-PTS with disclosure) | |
| moRequiredToItemize | No | the filer was REQUIRED to itemize federally (e.g. MFS with an itemizing spouse) — Missouri then requires itemizing even when the standard deduction is larger | |
| moResidentCreditYou | No | MO-1040 line 31Y: Form MO-CR credit for taxes paid to other states (agent-computed; the composer caps at line 30Y) | |
| njCollegeDependents | No | line 12 count: dependents under 22 attending college full-time (five months, half support) — $1,000 each ON TOP of the $1,500 line 10/11 exemption (use the shared dependents input for the $1,500 count) | |
| njPensionExcludable | No | NJ-1040 line 20b excludable (previously-taxed) pension/annuity/IRA amounts — display only | |
| njPropertyTaxesPaid | No | NJ-1040 line 40a: property taxes due and paid on the principal residence (homeowners; after Worksheet G proration). Tenants: use njRentPaid instead and the composer applies the 18% conversion. | |
| njSeHealthInsurance | No | self-employed health insurance deduction (Worksheet F line 5) | |
| njTaxExemptInterest | No | NJ-1040 line 16b tax-exempt interest (reported, never taxed) | |
| ohNonresidentCredit | No | OH Schedule of Credits line 38 nonresident credit (Ohio IT NRC, hand-computed) | |
| orAppliedToNextYear | No | OR-40 line 48: refund applied to 2026 estimated tax | |
| orFederal1040Line22 | No | federal Form 1040 LINE 22 (tax after nonrefundable credits) — the federal tax subtraction worksheet's line 1 (from compute_return, verbatim) | |
| orRegularExemptions | No | regular exemption count: 'yourself' + 'spouse' credit boxes (6a/6b) + dependents (6c) — $256 each, $0 cliff above $100,000 federal AGI (single/MFS) or $200,000 (others) | |
| orTaxMethodOverride | No | OR-40 line 20 alternate-method tax: farm income averaging (OR-FIA-40, box 20a), farm capital gain (Worksheet FCG, box 20b), or the IRREVOCABLE Oregon PTE reduced rate (OR-PTE-FY, box 20c) — agent-computed; wins over the table/chart tax | |
| paAbleContributions | No | Schedule O code A: PA ABLE contributions, capped at the federal gift-tax exclusion ($19,000 for 2025) | |
| paGrossCompensation | No | PA-40 line 1a: W-2 BOX 16 total (NOT Box 1 — 401(k)/elective deferrals are PA-taxable; eligible retirement distributions are exempt and excluded). Falls back to the shared wages input when omitted (composer discloses). Include taxable early-distribution amounts under the cost-recovery method. | |
| paPenaltiesInterest | No | PA-40 line 27: penalties and interest incl. estimated-underpayment penalty (REV-1630) | |
| paScheduleOcCredits | No | PA-40 line 23 component: Schedule OC restricted credits total (transcribed; no oracle target) | |
| paSpouseBusinessNet | No | PA-40 line 4, SPOUSE's own net business income or loss (kept separate: PA never nets one spouse's loss against the other's income) | |
| paSpousePropertyNet | No | PA-40 line 5, spouse's own net property gain/loss | |
| scAppliedToNextYear | No | SC1040 line 27: amount of the line 24 overpayment credited to 2026 estimated tax | |
| scSubtractionsOther | No | SC subtraction lines f/g/h/j/k/l/m/n/v total (state tax refund, total-and-permanent disability retirement, out-of-state non-personal-service income, volunteer firefighter/EMS/police $6,000 (2025), Future Scholar 529 (unlimited), ACTIVE TRADE OR BUSINESS income electing the I-335 3% flat tax (line l — must pair with scActiveTradeTax), US government interest, nontaxable Guard/Reserve pay, other) — EXCLUDING the composer-computed lines i/o/p/q/r/s/t/u/w | |
| vaAgeQualifyingFull | No | count of filers (taxpayer/spouse) born ON OR BEFORE January 1, 1939 — each gets the UNCONDITIONAL $12,000 age deduction (no income test) | |
| vaYourAgeBlindBoxes | No | STA worksheet Part 1 line 2: PRIMARY taxpayer's 65+/blind box count (0-2) — per-spouse exemption = boxes x $800 + $930 | |
| wiAppliedToNextYear | No | Form 1 line 42: overpayment applied to 2026 estimated tax | |
| wiPropertyTaxesPaid | No | property taxes on the principal residence (line 16b; 12% via the printed $25-wide-row table — a different granularity from the $100-row rent tables) — combined 16a+16b credit caps at $300 ($150 MFS or married-HOH); not claimable with the line 34 veterans credit | |
| wiScheduleUInterest | No | Form 1 line 44: Schedule U underpayment interest | |
| alFederalTaxPlusNiit | No | federal Form 1040 LINE 22 tax PLUS Form 8960 line 17 NIIT — the line 12 worksheet's gross federal tax (from compute_return, verbatim; NEVER the W-2 federal withholding) | |
| alItemizedDeductions | No | Alabama Schedule A total — differs from federal: FICA/Medicare/SE taxes ARE deductible, medical floor is 4% of AGI, NO federal income tax here (it's line 12), NEW 2025 vehicle-loan interest ≤$10,000 phased out $200 per $1,000 ceil-step of AGI over $100,000/$200,000-MFJ. The composer takes the larger of this or the AGI-phased standard deduction. | |
| alScheduleCpPayments | No | Form 40 line 26: payments from Schedule CP, Section B line 1 (composite payments) | |
| caAb5NetLossAddition | No | net losses from businesses where the worker is an employee for California (intake ca_form540_schca.add_net_loss) — the federal Schedule C loss is disallowed for CA: Schedule CA BUSINESS addition, col C | |
| caItemizedDeductions | No | CA itemized deduction total (Schedule CA Part II, line 29) — agent-computed per Schedule CA's own itemized rules WITH disclosure (differs from the federal Schedule A: no SALT cap, mortgage/medical add-backs, etc.). Form 540 line 18 takes the GREATER of this or the CA standard deduction; omit to use the standard deduction only. | |
| gaFederalCdccAllowed | No | federal Form 2441 line 11 allowed credit — GA IND-CR 202 pays 50% of it (us.ga.cdcc) | |
| mdEicQualifyingChild | No | the filer has at least one EIC qualifying child — with married filers this routes line 22 to 50% of the federal EIC (Worksheet 18A) and line 44 to the 45% refundable worksheet (21A); childless single/HOH/QSS filers instead get 100% refundable (18A.1). Also drives the Form 502 EIC checkboxes. | |
| mdSsRrBenefitsSpouse | No | spouse's TOTAL SS/RR benefits for their 13A column | |
| moActiveDutyMilitary | No | MO-1040 line 18: active duty military income deduction (100%, incl. annual training and — NEW 2025 — National Guard/reserve signing bonuses) | |
| moSubtractionsSpouse | No | the spouse's MO-A subtractions on the same terms | |
| moTrustFundDonations | No | MO-1040 line 51: trust fund donations total (51a-51l) | |
| ncMilitaryRetirement | No | NC Schedule S line 21: military retirement pay / SBP payments for members with 20+ years of service OR Chapter 61 medical retirement — never severance, never double-claimed with Bailey | |
| ncQualifyingChildren | No | D-400 line 10a: count of qualifying children for whom the federal § 24 child tax credit was ALLOWED (under 17; ODC-only dependents never count) — drives the AGI-tiered child deduction (us.nc.child_deduction) | |
| nonrefundableCredits | No | state NONREFUNDABLE credits without an oracle target — capped at the state tax due by the composer (an excess never creates a refund). VA: do NOT put the low-income credit or any VA EITC election here — passing it forces a legacy capped path; instead pass federalEITC (+ vaFamilyVagi if testing the low-income credit) and the composer computes and SELECTS the Form 760 line 23 credit itself (TY2025 refundable VA EITC = 20% of federal EIC, uncapped — it dominates whenever federal EITC > 0). IL: pass ICR raw inputs instead where fields exist. | |
| ohFederalCdccAllowed | No | federal Form 2441 line 11 (liability-limited allowed credit) — the Ohio CDCC pays 25% of it when MAGI is $20,000-$39,999 | |
| ohOtherCreditsPreJfc | No | OH Schedule of Credits lines 3+5+7+8 (lump sum retirement, lump sum distribution, displaced worker training, campaign contribution) — transcribed; they subtract BEFORE the joint filing credit's line-11 base | |
| orItemizedDeductions | No | Schedule OR-A line 23 OREGON itemized deductions (Oregon's own computation — never the federal Schedule A total). The composer takes the larger of this and the standard deduction. | |
| scConsumerProtection | No | SC line u: identity-theft/consumer protection services purchased after a security breach notification — the composer caps at $300 (individual) / $1,000 (joint or with dependents) | |
| scNetLtcgAfterLosses | No | net LONG-TERM capital gain held over one year, AFTER netting ALL capital losses (short-term included — the printed example nets an ST loss against the LT gain first) — the composer takes the 44% deduction (line i) | |
| vaItemizedCharitable | No | VA Sch A charitable contributions (federal Schedule A amount) | |
| vaItemizedOtherTaxes | No | VA Sch A line 6 other taxes (foreign income tax etc.) | |
| vaItemizedSalesTaxes | No | VA Sch A line 5a when the general SALES tax election was made federally — capped at the Virginia SALT cap ($40,000; $20,000 MFS for TY2025) | |
| wiItemizedComponents | No | Form 1 Schedule 1 lines 1-4 total: federal Schedule A medical + interest (EXCLUDING out-of-state second homes, boat residences, and U.S.-security carrying interest) + charity + casualty — the composer takes 5% of the excess over the line 8 standard deduction | |
| wiRetirement67Income | No | qualified-plan/IRA retirement income of the 67+ individual(s) for the NEW 2025 Act 15 subtraction (SB line 16, $24,000/$48,000 cap) — CAUTION: claiming it FORFEITS every credit on lines 13-20, 30-35, and Schedule CR (the composer enforces this); compare both ways before passing | |
| gaItemizedAdjustments | No | Form 500 line 12b: state income taxes in the federal Schedule A total plus the disallowed-SALT proration when the $10,000/$5,000 cap bound (printed formula, hand-computed) | |
| gaSpouseExclusionTier | No | spouse's GA retirement-exclusion tier (each spouse qualifies separately; never shared) | |
| mnAdvanceCtcRepayment | No | M1 line 14b: repayment of 2025 ADVANCE Child Tax Credit payments elected on the 2024 return (reconciliation, NEW for 2025) | |
| mnNetInvestmentIncome | No | Schedule NIIT Minnesota net investment income (federal 8960 concept minus class 2a agricultural-land gains) — the composer evaluates us.mn.niit (1% over $1,000,000) into line 14a | |
| mnSsAlternativeMethod | No | the M1M Worksheet ALTERNATIVE-method Social Security subtraction (steps 9-28, agent-computed, NET of the Tier 1 RR offset) — the composer takes the GREATER of this and the oracle simplified method when AGI exceeds the full-subtraction threshold (2025 alternative maxes: $5,840 MFJ/QSS, $4,560 single/HOH, $2,920 MFS) | |
| mnUnderpaymentPenalty | No | M1 line 27: Schedule M15 underpayment penalty | |
| moNetStateIncomeTaxes | No | MO-A Part 2 line 11: state/local income taxes from Schedule A line 5a MINUS Kansas City/St. Louis earnings taxes (which stay deductible) — or the Part 2 worksheet result when SALT exceeded $40,000/$20,000-MFS or FAGI exceeded $500,000/$250,000-MFS | |
| moPublicPensionSpouse | No | the spouse's public-source pension for their Section A column | |
| moUnderpaymentPenalty | No | MO-1040 line 55: Form MO-2210 underpayment penalty (90% / 66⅔%-farmer safe harbors) | |
| ncPartnershipPayments | No | D-400 line 21c: NC tax paid by a partnership on the filer's behalf | |
| njNjbestContributions | No | NJ-1040 line 37a NJBEST 529 contributions (composer caps at $10,000; all three 37a-c require gross income ≤ $200,000) | |
| orCarryforwardCredits | No | OR-40 line 30: Schedule OR-ASC line E9 carryforward credits used this year (capped at the remaining tax by the composer) | |
| orCharitableCheckoffs | No | OR-40 line 49: Schedule OR-DONATE charitable checkoffs (reduce the refund) | |
| orExcessAptcRepayment | No | excess advance premium tax credit repayment (1040 Schedule 2 line 1a) — SUBTRACTED in the worksheet (floor 0) | |
| orInstallmentInterest | No | OR-40 line 21: interest on installment-sale deferred tax liability (9% annual rate for 2025) | |
| paEligibilityAddbacks | No | Schedule SP Section III nontaxable add-backs (gifts, inheritances, insurance proceeds, non-PA income, nontaxable military pay, excluded home-sale gain, educational assistance, outside cash support). NOT Social Security, eligible retirement benefits, child support, or workers' comp. | |
| paMsaHsaContributions | No | Schedule O codes M/H: MSA + HSA contributions at the federally-allowed amounts | |
| paSpDependentChildren | No | Schedule SP dependent CHILDREN count (child/stepchild/adopted; grandchild of a grandparent; foster child of a foster parent — never other relatives) claimable as federal dependents; each adds $9,500 to the Tax Forgiveness eligibility-income threshold | |
| paStudentLoanInterest | No | Schedule O code S: student loan interest PAID (new deduction for 2025; the composer caps at $2,500 — pass the uncapped amount) | |
| scRetirementIncomeYou | No | primary taxpayer's qualified retirement income (401(k)/403(b)/457, IRA, Keogh — EXCLUDING military retirement, which goes in scMilitaryRetirementYou) — the composer caps at $3,000 under 65 / $10,000 at 65+ (line p-1; us.sc.retirement_deduction) | |
| scUnderpaymentPenalty | No | SC1040 line 33: underpayment of estimated tax penalty (SC2210 attached) | |
| taxableSocialSecurity | No | federally TAXABLE social security (Form 1040 line 6b, from compute_return). REQUIRED whenever nonzero: VA (760 line 5 subtraction), CA (Schedule CA line 6 col B), and NY (IT-201 line 27) all subtract it — the composer applies the subtraction automatically; do NOT also fold it into the generic subtractions total. | |
| vaAgeQualifyingTested | No | count of filers born January 2, 1939 - January 1, 1961 (65+ for 2025 but income-tested): the composer computes $12,000 each, reduced dollar-for-dollar by AFAGI over $50,000 single / $75,000 married — where AFAGI = federal AGI MINUS the federally taxable social security (the SS exclusion is the step agents miss; Va. Code § 58.1-322.03(2)) | |
| vaSpouseAgeBlindBoxes | No | STA worksheet Part 1 line 2: spouse's 65+/blind box count (0-2) | |
| vaSpouseTaxAdjustment | No | OVERRIDE ONLY — the composer now computes the VA Spouse Tax Adjustment worksheet itself when vaYourVagi/vaSpouseVagi are provided. If passed, this amount wins. | |
| wiBlindWorkerExpenses | No | blind worker transportation services qualifying expenses (Form 1 line 15 credits 50%) | |
| wiRentHeatNotIncluded | No | rent with heat NOT included (line 16a; 3.0% table) | |
| alTaxableRetirementYou | No | primary taxpayer's OTHERWISE-TAXABLE retirement income (IRA/401(k)/SEP/Keogh/403(b) distributions after basis recovery) — defined-BENEFIT pensions, Social Security, Railroad Retirement, military, and US/AL government retirement are 100% EXEMPT and never entered. The composer applies the 65+ $6,000 Schedule RS exclusion (us.al.retirement_exclusion). | |
| caDepreciationAddition | No | CA depreciation-difference addition: federal depreciation (with § 168(k) bonus, which California NEVER conforms to) minus CA depreciation (plain MACRS on the same asset). Positive = CA income addition (Schedule CA col C on the business/rents line). Compute per-asset and disclose. | |
| mnWildlifeContribution | No | M1 line 18: Nongame Wildlife Fund contribution (reduces the refund) | |
| moBusinessIncomeSpouse | No | the spouse's net business income for the 20% deduction (17S) | |
| moEnterpriseZoneSpouse | No | MO-1040 line 28S | |
| moInactiveDutyMilitary | No | MO-1040 line 19: inactive duty (drill) military income deduction | |
| moPrivatePensionSpouse | No | the spouse's private-source pension for Section B | |
| moResidentCreditSpouse | No | MO-1040 line 31S (capped at 30S) | |
| ncUnderpaymentInterest | No | D-400 line 26e: interest on the underpayment of estimated income tax (Form D-422) | |
| ncUsObligationInterest | No | NC Schedule S line 18: interest from US obligations (Treasuries, savings bonds) included in FAGI — fully deducted | |
| njUnderpaymentInterest | No | NJ-1040 line 52 interest on underpayment of estimated tax (Form NJ-2210) | |
| ohFederalCdccTentative | No | federal Form 2441 line 9c (tentative credit before the federal liability limit) — the Ohio CDCC pays 100% of it when MAGI < $20,000 | |
| orDisabilityExemptions | No | severe-disability boxes (6a/6b) + children with a qualifying disability (6d) — $256 each, $0 cliff above $100,000 federal AGI for EVERY filing status | |
| paSpouseRentRoyaltyNet | No | PA-40 line 6, spouse's own net rent/royalty amount | |
| paUnreimbursedExpenses | No | PA-40 line 1b: Schedule UE unreimbursed employee business expenses (a compensation-class expense, never a line-10 deduction) | |
| scFederalTaxableIncome | No | REQUIRED for SC: federal Form 1040 line 15 TAXABLE income (from compute_return, verbatim) — the SC1040 line 1 starting point (NOT federal AGI). A NEGATIVE amount is allowed: the composer enters $0 on line 1 and preserves the loss on subtraction line r per the printed instructions. | |
| spouseStateWithholding | No | VA line 19b spouse withholding (spouse's own W-2/1099/VK-1 boxes + spouse's half of jointly-issued documents' withholding, odd dollar to the primary) | |
| wiScheduleIAdjustments | No | Form 1 line 2: Schedule I net adjustment (may be negative) converting federal AGI to Wisconsin's IRC — Wisconsin conforms to the Code as of December 31, 2022, so post-2022 federal changes (incl. the 2025 OBBBA) need Schedule I conversion per its instructions | |
| mdNetCapitalGainSubject | No | Form 502CG line 9: net capital gain subject to the H.B. 352 2% surtax (line 1c gain minus the six exempt classes — primary-residence sale under $1.5M, retirement-plan assets, livestock, easement land, trade-or-business property, nonprofit affordable housing). The composer zeroes it (with a note) unless FAGI exceeds $350,000. | |
| mnDependentEarnedIncome | No | dependent-claimed filer's earned income for the dependent standard-deduction worksheet (lesser of the table amount or max($1,250, earned + $350)) | |
| ncClaimOfRightRepayment | No | NC Schedule A line 8: claim-of-right repayments over $3,000 (deducted in full) | |
| njOrganDonationExpenses | No | NJ-1040 line 36 organ/bone-marrow donation expenses (composer caps at $10,000) | |
| njPensionEligibleAmount | No | joint returns where only ONE spouse is 62+/disabled: that spouse's share of line 20a (the exclusion never covers the ineligible spouse's pension). Defaults to all of line 20a. | |
| orDependentEarnedIncome | No | dependent-claimed filer's earned income — the standard deduction is limited to max($1,350, earned + $450), capped at the Table 5 amount | |
| scMilitaryRetirementYou | No | primary taxpayer's military retirement income — 100% deductible since TY2022 (line p-4); per the printed worksheet it REDUCES the same person's retirement-deduction CAP and age-65 deduction (instructions Example 5: $16,000 military at 65+ leaves $0 on lines p-1 and q-1) — the composer handles the interplay | |
| vaScheduleAdjDeductions | No | Schedule ADJ line 9 total deductions (deduction CODES like 105 continuing-teacher-education, 199 other) — prints on Form 760 line 13; these are DEDUCTIONS from VAGI, never income subtractions on line 7 | |
| wiDependentEarnedIncome | No | a dependent-claimed filer's earned income for the Standard Deduction Worksheet for Dependents (deduction = smaller of the table amount or max($1,350, earned + $450)) | |
| wiEicQualifyingChildren | No | federal-EIC qualifying children — Wisconsin EIC = 4%/11%/34% of the federal credit for 1/2/3+ children (NO childless credit; MFS ineligible; full-year residents only) | |
| caAb5GrossIncomeAddition | No | gross income from businesses where the worker is classified as an EMPLOYEE for California (AB 5/Dynamex reclassification; the intake's ca_form540_schca.add_gross_income field) — Schedule CA WAGE addition, col C | |
| caHsaTaxableDistribution | No | HSA distribution amount taxed federally (Form 8889 line 16) — not income for California: the composer SUBTRACTS it for CA | |
| gaEligibleItemizerCredit | No | Form 500 line 19: Georgia Eligible Itemizer Tax Credit (NEW 2025; up to $300 per taxpayer, itemizers with 183+ GA days or resident at year end) — TRANSCRIBE the worksheet-computed amount, never assume the full $300; composer caps at $300/$600 | |
| gaRetirementEarnedIncome | No | primary taxpayer's earned income — at most $5,000 counts inside the exclusion (Schedule 1 worksheet) | |
| gaSpouseRetirementIncome | No | spouse's unearned retirement income for the exclusion | |
| moWftcInvestmentOver4400 | No | Form MO-WFTC question 3: investment income exceeds $4,400 — denies the credit. The MO credit follows EIC law FROZEN as of January 1, 2021 (MO-1040 instructions p.10), so this is the indexed pre-ARPA limit; compute investment income the pre-2021 way (taxable AND tax-exempt interest, dividends, positive net capital gain per the MO-WFTC instructions), NOT the current federal $11,950 gate. | |
| orPoliticalContributions | No | 2025 cash contributions to qualified Oregon political parties/candidates/PACs — the composer caps at $50 ($100 joint) and denies above $75,000/$150,000 federal AGI | |
| orPoliticalPartyCheckoff | No | OR-40 line 50: political party $3 checkoff from the refund | |
| scRetirementIncomeSpouse | No | spouse's qualified retirement income for line p-2 (each spouse's own cap; joint returns) | |
| unemploymentCompensation | No | unemployment compensation included in federal AGI (Schedule 1 line 7). REQUIRED whenever nonzero: VA fully subtracts it (Va. Code § 58.1-322.02(9), Schedule ADJ) and CA excludes it (Schedule CA line 7 col B) — the composer subtracts automatically for those states; do NOT also fold it into the generic subtractions total. IL and NY tax it (no subtraction). | |
| wiCapitalGainSubtraction | No | Schedule SB line 5 capital gain/loss subtraction from Schedule WD (30% net long-term gain exclusion, 60% farm assets; capital loss limit $3,000/$1,500-MFS since TY2023; simple mutual-fund/REIT distributions may take 30% directly) | |
| alTaxableRetirementSpouse | No | spouse's otherwise-taxable retirement income (Schedule RS Part III) | |
| mdItemizedStateLocalTaxes | No | MD line 17b: state and local INCOME taxes claimed in the federal Schedule A (plus preservation-easement contributions claimed as a credit) — subtracted from 17a | |
| njOtherRetirementEligible | No | line 28b Worksheet D gate: filer is 62 or older (the composer auto-computes the unclaimed exclusion when earned income ≤ $3,000 and line 27 ≤ $100,000) | |
| njShelteredWorkshopCredit | No | NJ-1040 line 46 Sheltered Workshop Tax Credit (GIT-317) | |
| orFederalOtherIncomeTaxes | No | other INCOME taxes from Schedule 2 lines 8, 16, 17 (income-tax recaptures only — never SE tax, SS/Medicare tip tax, household employment taxes, penalties, or excise) | |
| vaItemizedRealEstateTaxes | No | VA Sch A line 5b real estate taxes — NOT subject to the SALT cap for Virginia | |
| alFederalRefundableCredits | No | the line 12 worksheet's refundable-credit subtraction: 1040 line 27a EIC + line 28 ACTC + line 29 AOC + line 30 refundable adoption + Schedule 3 Part II line 13a Form 2439 credits | |
| caEducatorExpensesDeducted | No | federal educator-expense deduction claimed (§ 62(a)(2)(D)) — California does NOT conform: the composer ADDS it back on Schedule CA (line 11 col C). Pass the federal amount actually deducted (both spouses' combined). | |
| caTaxableEarlyDistribution | No | retirement-plan early distribution amount subject to the FEDERAL § 72(t) additional tax — California imposes its own 2.5% additional tax on the same base (R&TC § 17085(c)(1), FTB 3805P); the composer computes 2.5% and prints it on Form 540 line 63 | |
| mdTwoIncomeLesserSpouseNet | No | Worksheet 13D line 6: the LESSER-income spouse's net Maryland income (their FAGI share + additions share − subtractions share) — the composer caps it at $1,200 for line 14 (joint returns only) | |
| njConservationContribution | No | NJ-1040 line 33 qualified conservation contribution (NJ land, federal amount) | |
| njOrganDonorEmployerCredit | No | NJ-1040 line 48 employer of organ/bone-marrow donor credit (25% of salary, up to 30 days) | |
| njOtherRetirementExclusion | No | OVERRIDE: hand-computed Worksheet D line 9 unclaimed exclusion (required for the $100,001-$150,000 percentage tiers) | |
| scMilitaryRetirementSpouse | No | spouse's military retirement income (line p-5) | |
| vaItemizedMortgageInterest | No | VA Sch A home mortgage interest and points (federal Schedule A amount) | |
| moStandardDeductionOverride | No | dependent-claimed filers: the federal DEPENDENT standard deduction limit (greater of $1,350 or earned income + $450, capped at the full amount) — replaces the composer's full standard deduction | |
| orFederalRefundableAdoption | No | refundable adoption credit (1040 line 30) — subtracted | |
| priorYearOverpaymentCredited | No | prior-year state overpayment applied toward this year's estimated tax. VA 760 line 21 (its own printed line — never fold into line 20 estimated payments). Other states: folded into the estimated-payments line. | |
| scLowerQualifiedEarnedIncome | No | the LESSER-earning spouse's SC qualified earned income per the Two Wage Earner worksheet (earned income minus attributable federal adjustments) — line 12 credit = 0.7% capped at $50,000 base / $350 credit; MFJ only (us.sc.two_wage_earner_credit) | |
| vaItemizedInvestmentInterest | No | VA Sch A investment interest (protected from the overall limitation) | |
| wiFederalRetirementPenalties | No | the FEDERAL penalties on IRAs/retirement plans/MSAs etc. — Wisconsin charges 33% of them on line 25 ('x .33' printed) | |
| wiLowerQualifiedEarnedIncome | No | the LESSER-earning spouse's Schedule 2 line 5 qualified earned income (earned income minus the listed federal Schedule 1 adjustments) — married couple credit = 3% up to $480 (joint returns, both spouses employed) | |
| alFederalTaxDeductionOverride | No | OVERRIDE for Form 40 line 12: the RATIOED federal tax for joint-federal/separate-Alabama returns (by each spouse's FAGI share) or part-year residents (AL-AGI/FAGI ratio) — wins over the composer's oracle computation | |
| ohBothSpousesQualifyingIncome | No | joint filing credit gate: EACH spouse has $500+ of qualifying income included in Ohio AGI (not interest/dividends/capital gains/rents, and not BID-deducted business income or deducted Social Security/retirement) | |
| orFederalTaxLiabilityOverride | No | OVERRIDE for the worksheet line 10 result (amended federal returns, foreign income tax, 1040-NR, recapture situations — Publication OR-17 worksheets); the Table 4 AGI cap still applies via the oracle | |
| gaSpouseRetirementEarnedIncome | No | spouse's earned income for the exclusion worksheet | |
| mdChildCareTwoOrMoreDependents | No | two or more care dependents — raises the MD line 9 expense cap from $3,000 to $6,000 | |
| vaItemizedPersonalPropertyTaxes | No | VA Sch A line 5c personal property taxes — NOT subject to the SALT cap for Virginia | |
| vaItemizedStateLocalIncomeTaxes | No | VA Sch A line 5a when INCOME taxes are claimed (mutually exclusive with sales taxes) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full transparency burden and delivers extensively. It discloses determinism, which jurisdiction starts from which base ('NC and GA start from federalAGI', 'federalAGI is NOT the PA or NJ base', 'For SC, the base is FEDERAL TAXABLE INCOME'), what the composer computes internally vs. what the agent must compute, gate rules (e.g., the false-boolean array gate for additions/subtractions), and side effects like the Wisconsin Act 15 forfeiture: 'the SB-16 retirement subtraction FORFEITS every credit — the composer enforces the forfeiture.' It also states exclusions and refusal behaviors (composer 'refuses without' federalAGI for certain states). No contradictions with the (empty) annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extraordinarily long — a dense wall of prose with state-specific rules running together without section markers, bullets, or line breaks (e.g., NC, GA, PA, NJ, OH, MD, MO all flow in one continuous paragraph). While nearly every sentence carries substantive information (so it's not padding), the lack of structure hurts scannability for an agent, and it is not 'front-loaded' — it dives into state minutiae immediately rather than giving a top-level workflow or return-value summary first. It is appropriately sized given the 386-param/16-state complexity, but poorly organized, warranting a 3 rather than higher.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the extreme complexity (386 parameters, 16 jurisdictions, no annotations, no output schema), the description is remarkably comprehensive. It covers the full workflow, state-specific computational bases, what the composer runs internally (e.g., 'the composer runs the AGI-tiered child deduction', 'the composer evaluates us.sc.retirement_deduction'), which components the agent must compute and disclose, payment/refund-related conventions (e.g., extensionPayment line differences for VA vs NY), and state-specific exceptions and prohibitions. It also addresses edge cases like negative amounts (SC line r, MO negative-share zeroing) and proration rules. With no output schema, the description's role in defining the produced line set is well fulfilled.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 99%, so the baseline is 3, and the main description correctly leaves most parameter detail to the schema. However, the description adds meaningful orchestration-level semantics for parameters whose interactions matter: it flags required-pass-when-nonzero parameters (taxableSocialSecurity, unemploymentCompensation for VA/CA/NY), per-state base inputs (scFederalTaxableIncome, alWages as 'W-2 Box 16', moFagiYou/moFagiSpouse splitting rules), and interplay constraints (SC military retirement 'REDUCES the same person's other two deductions'). It also gives anti-patterns (e.g., do not fold taxableSocialSecurity into generic subtractions, don't put SC EITC in nonrefundableCredits). This raises it above the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb-resource pairing: 'Compose a STATE return's printed-form line set deterministically' for a defined list of 16 U.S. state forms (IL-1040, VA 760, CA 540, etc.). It clarifies scope (deterministic line numbers, whole-dollar rounding) and implicitly distinguishes from sibling compute_return ('run compute_return first for the federal substrate', implying this tool is the state-level counterpart). It also states what it does NOT do (e.g., Maryland part-year returns, Kansas City/St. Louis earnings taxes), further sharpening the purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides an explicit Workflow section: 'run compute_return first for the federal substrate, compute any state-specific components the citations describe... then call this ONCE and report its line set VERBATIM.' It gives clear when-to-use guidance (after the federal substrate) and a strong when-not-to instruction: 'Never hand-assemble state line numbers.' It also flags alternatives (e.g., 'Kansas City/St. Louis 1% earnings taxes are separate city returns the composer does not produce'), directing the agent away from this tool for those cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
determine_dependentAInspectDetermine whether ONE candidate person is the taxpayer's § 152 dependent — qualifying child or qualifying relative, including multiple-support agreements and the divorced-parents release — as a proof-backed yes/no with citations. Feed the result into calculate_tax's credits group (qualifyingChildren / otherDependents).
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | REQUIRED for computation: the law-in-force date — use the intended tax year's year-end (e.g. "2025-12-31" for TY2025). Omitting it is an error, never a default. | |
| depAge | No | Candidate's age at the end of the year (§ 152(c)(3)). | |
| target | No | rule to derive (default: us.federal.dependent.is_dependent). Other targets: us.federal.dependent.qualifying_child, us.federal.dependent.qualifying_relative | |
| depGrossIncome | No | Candidate's gross income for the year (§ 152(d)(1)(B) limit: $5,200 TY2025 / $5,300 TY2026). In dollars. | |
| depFilesJointReturn | No | Candidate files a joint return with a spouse (other than a refund-only claim) (§ 152(c)(1)(E)). | |
| depIsFullTimeStudent | No | Candidate was a full-time student for at least 5 months (§ 152(f)(2)). | |
| depRelationshipChild | No | Candidate is the taxpayer's child, stepchild, foster child, sibling, step-sibling, or a descendant of any of them (§ 152(c)(2)). | |
| depDivorcedParentsRule | No | § 152(e) applies to the candidate child: the parents are divorced, separated, or lived apart the last 6 months of the year; the child received over half their support from the parents and was in their custody over half the year. | |
| depPermanentlyDisabled | No | Candidate is permanently and totally disabled (§ 152(c)(3)(B)). | |
| depYoungerThanTaxpayer | No | Candidate is younger than the taxpayer (§ 152(c)(3)(A)). | |
| depRelationshipRelative | No | Candidate bears a § 152(d)(2) relationship to the taxpayer (parent, grandparent, sibling, in-law, etc.) or lived in the household all year. | |
| taxpayerIsCustodialParent | No | The taxpayer is the custodial parent (the parent with whom the child resided the greater number of nights, § 152(e)(4)(A)). | |
| hasMultipleSupportAgreement | No | A § 152(d)(3) multiple-support agreement is in place for the candidate: the group together provided over half the support, no one person provided over half, each member could otherwise claim the candidate, and every other over-10% contributor signed a Form 2120 waiver. | |
| custodialParentReleasedClaim | No | The custodial parent signed a written declaration (Form 8332) releasing the claim to the child for this year (§ 152(e)(2)). | |
| depIsQualifyingChildOfAnother | No | Candidate is the qualifying child of the taxpayer or any other taxpayer (§ 152(d)(1)(D)). | |
| depProvidedOwnSupportOverHalf | No | Candidate provided more than half of their own support (§ 152(c)(1)(D)). | |
| taxpayerProvidedOverHalfSupport | No | The taxpayer provided more than half of the candidate's support (§ 152(d)(1)(C)). | |
| depLivedWithTaxpayerOverHalfYear | No | Candidate had the same principal residence as the taxpayer for more than half the year (§ 152(c)(1)(B)). | |
| taxpayerProvidedOver10PercentSupport | No | The taxpayer contributed over 10 percent of the candidate's support (§ 152(d)(3)(D) — the support test under a multiple-support agreement). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. The description states it returns a 'proof-backed yes/no with citations,' but does not disclose behavioral traits such as side effects, required inputs, error handling, or any limitations. For a tool with 19 parameters and no output schema, more behavioral context is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose and scope, followed by usage guidance. Every sentence adds value, and there is no wasted verbiage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (19 parameters, no output schema), the description explains what the tool does and how to use the result, but does not fully cover the return format beyond 'yes/no with citations' or guide on parameter usage. The schema descriptions handle parameter details, but the description could be more complete by elaborating on the output structure and input expectations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so each parameter already has a description. The tool description does not add any parameter-level details beyond what the schema provides. Baseline is 3, and the description does not compensate for any gaps or add extra meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states what the tool does: determine if a candidate is a dependent under §152, specifying 'qualifying child or qualifying relative' and mentioning special cases like multiple-support agreements and divorced-parents release. It also states the output is a 'proof-backed yes/no with citations' and provides guidance to feed into calculate_tax. This is specific and distinguishes from sibling tools like calculate_tax.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for checking dependency status before tax calculation by saying 'Feed the result into calculate_tax's credits group.' It provides clear context when to use it, but does not explicitly state when not to use it or mention alternatives among siblings like verify_fact or verify_tax_claim, which might handle similar claims.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
explain_ruleAInspectGet a tax rule's statutory citation, verbatim excerpt, validity window, parameters, and dependencies. Use to quote the actual law behind an answer.
| Name | Required | Description | Default |
|---|---|---|---|
| ruleId | Yes | e.g. "us.federal.standard_deduction" — list via calculate_tax proof or corpus |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It fully discloses the return fields (citation, excerpt, validity window, parameters, dependencies), which implies a read-only, non-destructive operation. It does not mention prerequisites or side effects, but given the tool's explanatory nature, this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at two sentences. The first sentence front-loads the purpose and outputs, and the second provides the usage context. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (1 required parameter, no output schema, no enums, no nesting), the description adequately covers the tool's purpose, outputs, and use case. It does not mention error conditions, but that is not necessary for a straightforward explanatory tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema coverage is 100% with a helpful description for ruleId (example value and source). The description adds value by explaining what the tool returns, which helps the agent understand how the parameter contributes to the output. Since coverage is high, the description meaningfully supplements the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states what the tool does: 'Get a tax rule's statutory citation, verbatim excerpt, validity window, parameters, and dependencies.' It also specifies the use case: 'Use to quote the actual law behind an answer.' This distinguishes it from siblings like search_tax_rules (finding rules) and calculate_tax (computing taxes).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear context for when to use the tool ('to quote the actual law behind an answer'), but does not explicitly mention when not to use it or compare with siblings. However, the context is sufficient for an agent to infer appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
find_tax_cliffsBInspectFind exact dollar amounts where one more cent of an input costs MORE than a cent of tax (marginal rate over 100%) — e.g. the EITC investment-income kill switch, CTC phase-out steps. Every probe is a real evaluation.
| Name | Required | Description | Default |
|---|---|---|---|
| vary | Yes | money fact to vary, e.g. "wages" or "taxableInterest" | |
| facts | Yes | facts for the computation: either flat corpus fact ids (see list_input_facts) or the same group objects calculate_tax accepts (filing, income, retirement, …), plus optional target and asOf. Business/fiduciary/dependent facts are accepted flat. Unknown keys are rejected by name — nothing is ever silently dropped. | |
| toDollars | Yes | ||
| fromDollars | Yes | ||
| stepDollars | No | coarse scan step, default 1000 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description mentions 'every probe is a real evaluation,' suggesting actual tax calculations, but does not disclose performance, side effects, authentication needs, or rate limits. Lacks rich behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a parenthetical, no fluff, and front-loads the core purpose. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and moderate complexity, the description fails to explain what the tool returns, how the facts object is structured, or the scanning logic beyond 'real evaluation.' Incomplete for agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 60%, but the tool description adds no additional meaning beyond schema. The parameters (vary, facts, fromDollars, toDollars, stepDollars) are not elaborated. For example, stepDollars default is only in schema. Description does not compensate for uncovered parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool finds exact dollar amounts where marginal tax rate exceeds 100% (tax cliffs), with specific examples like EITC and CTC. It distinctively identifies unique functionality among siblings, which are mostly calculation or fact tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for finding tax cliffs but provides no explicit guidance on when to use or avoid this tool versus alternatives like calculate_tax or search_tax_rules. No when-not-to guidelines.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
is_tipped_occupationAInspectDetermine whether a job is on the Treasury Tipped Occupation list (Treas. Reg. § 1.224-1, final Apr 2026) for the § 224 'no tax on tips' deduction. Fuzzy-matches the job name; returns the official listing (name, TTC code, category) or a definitive 'not listed'.
| Name | Required | Description | Default |
|---|---|---|---|
| job | Yes | e.g. "bartender", "software engineer", "DJ" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the fuzzy-matching nature and the return value (official listing or 'not listed'). It does not mention side effects or permissions, but as a read-only query, this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences. It front-loads the purpose and regulatory reference, then details the behavior. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (one parameter, no output schema), the description is complete. It explains the input and output sufficiently. No additional context like rate limits is expected for such a tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of parameters with examples. The description adds value by explaining fuzzy matching on the job name, which goes beyond the schema's static description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: checking if a job is on the Treasury Tipped Occupation list for the §224 deduction. It specifies the regulation, the fuzzy-matching behavior, and the output format, distinguishing it from sibling tools that focus on calculations or other lookups.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool (to determine tip deduction eligibility) and implies it's a lookup. It does not explicitly mention when not to use it or list alternatives, but the context of sibling tools provides implicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_input_factsAInspectDiscover every input the tax corpus understands: id, type, whether required, and its documented default. Call this if unsure what information to collect from the user.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes the output as listing inputs, which is clear, but does not disclose potential side effects, authentication needs, or performance considerations. For a read-only listing, this is adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first defines purpose and output, second gives usage guidance. No redundant or vague language. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no parameters and no output schema, but the description fully explains its function and return contents. It tells the agent to use it for user data collection, providing complete context for a simple listing tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, so baseline is 4. The description adds meaning by specifying what attributes are returned (id, type, required, default), which helps the agent understand the tool's output beyond the empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool discovers every input the tax corpus understands, listing specific attributes (id, type, required, default). This distinguishes it from sibling tools that calculate, verify, or search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises to call this when unsure what information to collect from the user, providing a direct usage context. It could be improved by mentioning when not to use it, but the guidance is strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
lookup_tax_parameterAInspectLook up the current-law dollar amounts behind a question ('standard deduction', 'CTC phase-out threshold', 'tips deduction cap') with their statutory citations and validity windows. Use this to fact-check ANY tax number before stating it — your training data likely predates the OBBBA.
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | ||
| query | Yes | plain-English search, e.g. 'standard deduction' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description discloses that it returns current-law amounts, statutory citations, and validity windows. It also warns about outdated training data, which is helpful. It does not mention error handling or read-only nature, but the intended behavior is clear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: the first clearly defines purpose and output, the second provides usage guidance. Every sentence is valuable and there is no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple lookup tool with 2 parameters and no output schema, the description covers what it returns (citations, windows) and when to use it. It lacks details on what happens for missing queries or the exact format of citations, but it is largely sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (query has description, asOf only has pattern). The description adds value by explaining query as 'plain-English search' with an example. However, the asOf parameter lacks semantic explanation beyond the date pattern, leaving ambiguity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool looks up current-law dollar amounts behind specific tax questions, provides examples like 'standard deduction' and 'CTC phase-out threshold', and explicitly says it returns statutory citations and validity windows. This distinguishes it from sibling tools like verify_fact or search_tax_rules.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises to 'fact-check ANY tax number before stating it' because training data may be outdated. It implies the primary use case but does not explicitly mention when not to use it or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_tax_rulesAInspectFull-text search over the encoded tax-law corpus ('kiddie tax', 'NIIT threshold', 'california renters credit'). Returns matching rules: id, title, statutory citation, effective window, and a verbatim excerpt of the law text. A hit means the engine computes this; zero hits means it is outside the corpus — say so rather than guessing. Follow up with explain_rule for a hit's full formula, or lookup_tax_parameter for its dollar amounts.
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | ||
| limit | No | ||
| query | Yes | plain-English search, e.g. 'kiddie tax' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description effectively conveys the read-only search behavior, what a hit means, and the return format. However, it does not mention any rate limits, authentication needs, or performance characteristics, leaving minor gaps in behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two succinct sentences followed by a single directive sentence. All information is front-loaded and relevant, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (3 parameters, no output schema), the description provides sufficient context: purpose, return fields, interpretation of results, and links to sibling tools. It is complete enough for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 33% (only query described). The description adds a plain-English example for the query parameter but does not clarify the purpose or format of asOf and limit. The baseline compensation is minimal, leaving these parameters under-documented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it performs full-text search over a tax-law corpus, provides example queries, and details the return fields (id, title, citation, window, excerpt). It distinguishes itself from sibling tools by specifying follow-up tools like explain_rule.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells the agent to interpret zero hits as meaning the query is outside the corpus and not to guess. Also directs to use explain_rule or lookup_tax_parameter for further details, providing clear actionable guidance on when to use which tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
verify_factAInspectFact-check a claimed dollar amount about tax law ('the 2026 MFJ standard deduction is $32,200', 'CTC is $2,000 per child') against the corpus. Returns verified / refuted (with the correct value and citation) / unknown. Never states a verdict it cannot ground.
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | ||
| query | Yes | what the amount is, e.g. 'standard deduction' | |
| filingStatus | No | ||
| claimedAmount | Yes | dollars, e.g. 50000 or "1234.56" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It clearly states return values (verified/refuted with correct value and citation, unknown) and the grounding constraint, providing good transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words. Front-loaded with verb and resource, then return types and behavioral rule. Efficient and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has 4 params, no output schema. Description explains purpose, output types, and a behavioral rule. Missing details on optional parameters (asOf, filingStatus) and how they affect results, leaving some gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (2 of 4 params have descriptions). The description adds no extra meaning to parameters like 'asOf' or 'filingStatus' beyond examples. It does not compensate for missing schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fact-checks a claimed dollar amount about tax law, with examples. It distinguishes from sibling 'verify_tax_claim' but not explicitly, and is specific about the resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for fact-checking dollar amounts but lacks explicit when-to-use or alternatives. It includes a behavioral rule ('Never states a verdict it cannot ground') but no guidance on when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
verify_tax_claimAInspectVerify a claimed tax amount (yours, a user's, or another tool's) against the law. Returns verdict 'verified' or 'refuted' with the correct value. Use this as a self-check before presenting any tax number. Put asOf (and target, if any) INSIDE the facts object — e.g. facts: {..., "asOf": "2025-12-31"} — otherwise the claim is checked under today's law.
| Name | Required | Description | Default |
|---|---|---|---|
| facts | Yes | facts for the computation: either flat corpus fact ids (see list_input_facts) or the same group objects calculate_tax accepts (filing, income, retirement, …), plus optional target and asOf. Business/fiduciary/dependent facts are accepted flat. Unknown keys are rejected by name — nothing is ever silently dropped. | |
| claimedAmount | Yes | the amount to verify (negative = refund) | |
| toleranceDollars | No | default 1 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the return values (verdict and correct value), the fact that unknown keys are rejected (not silently dropped), and implies that without 'asOf', the law as of today is used. This is sufficient for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise: two sentences and a usage note. Every sentence adds value, and the critical placement rule is front-loaded. No redundant or vague phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (3 params, nested objects, 14 siblings), the description covers purpose, usage, parameter semantics, and behavioral constraints. It lacks details on error handling or invalid facts, but overall is sufficient for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. The description adds meaning beyond schema: explains that 'facts' can be flat IDs or group objects, notes 'negative = refund' for claimedAmount, and gives default toleranceDollars=1. It also clarifies that 'asOf' and 'target' must be inside facts, enhancing parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Verify a claimed tax amount against the law.' It explicitly specifies the return values ('verified' or 'refuted' with correct value) and distinguishes itself from sibling tools like verify_fact by targeting tax claims specifically. The scope (yours, a user's, or another tool's) is also clarified.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises: 'Use this as a self-check before presenting any tax number,' providing clear context. It also gives critical placement instructions for 'asOf' and 'target' inside the facts object. However, it does not explicitly state when not to use this tool or compare it to alternatives like verify_fact.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
