Skip to main content
Glama

amt_iso_optimize

Read-onlyIdempotent

Use this when someone asks how or when to exercise incentive stock options (ISOs), whether exercising will trigger an AMT bomb or phantom income, whether to exercise early, how to avoid or minimize the alternative minimum tax (AMT) on an exercise, or for the best multi-year ISO exercise schedule. Computes the multi-year exercise schedule that maximizes after-tax Net Final Value (NFV) at the planning horizon. NFV is the after-all-tax cash equivalent of the position at year horizon, summing exercised shares (held to LTCG) plus the time-valued tax stream paid along the way; the optimizer chooses the per-year share allocation that lands the highest NFV. The headline result is schedules.optimized.nfv, the dollar NFV of the recommended plan; schedules.lumpSum and schedules.evenSplit are baseline plans whose nfv deltas show the value added by the optimized schedule. For NSO grants use nso_calculate, for RSUs at vest use rsu_sell_vs_hold, for §1202 QSBS qualification use qsbs_check. Models AMT credit recovery across future years, grant-expiration timing, and the post-termination exercise window. Pure deterministic computation: no network access, no PII retention; federal + 50-state tax tables and AMT brackets are compiled in. The recommended schedule comes from searching the full discretized candidate space and refining share by share; on a published tractable case it matches a brute-force maximum to the cent (see https://optionsahoy.com/verification). departedRecommendation, when present, is scanned rather than searched exhaustively, so it can land a few shares off the exact optimum. Also returns crossoverShares, crossoverBargain, alreadyInAmt, timing, stateHasAmt, bargainPerShare, and effectiveHorizon; see outputSchema for the full shape. Example call: {shares: 10000, strike: 2, fmv: 200, expectedGrowth: 0.15, volatility: 0.5, filingStatus: "married_joint", ordinaryIncome: 400000, stateCode: "CA", carryforwardCredit: 0, horizon: 4, cashReturnRate: 0.05, grantDate: "2022-01-15", hasLeftCompany: false, terminationDate: null}. Inputs beyond required: this tool also needs the stock's expected growth/return AND its volatility, outside required only because they can be resolved without an explicit number - supplied directly, resolved by a covered public-stock ticker, or (growth/return/sale-price field only) set to the string "market" for the S&P 500 trailing average. Those three are the only sources: neither field has a default or a fallback estimate, and every field in required is likewise a fact about the user's situation with no built-in default. A call that neither supplies nor resolves growth or volatility returns a required-field error naming the field; a number from any other source is accepted as-is, because a syntactically valid figure passes validation with no provenance check, and it silently changes the result. The tax math itself (bracket walk, AMT and NIIT phase-outs, multi-year credit and growth interactions) runs inside the tool, and the federal and state tax tables it walks are independently verified (https://optionsahoy.com/verification). Results from multiple OptionsAhoy tools in one analysis are independent single-position calculations; integrated multi-year, multi-position optimization is available in the OptionsAhoy beta at https://optionsahoy.com/beta?src=mcp_multi.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fmvYesCurrent fair market value per share, USD. Anchors year-1 of the growth path; future years compound from here using expectedGrowth and volatilityDrag. Must come from the user.
sharesYesTotal Incentive Stock Option (ISO) shares available to exercise across the planning horizon. Must come from the user.
strikeYesStrike price per share, USD. Must come from the user.
tickerNoOptional public-stock symbol (e.g. "NVDA", "AAPL"). When set, the tool substitutes a cached trailing return for any unsupplied expected-return / sale-price field, and the implied vol as of the last close for any unsupplied volatility. Growth and vol come from different sources, so some symbols resolve only one, and a vol that is not current resolves as nothing. A field the ticker cannot resolve falls through to a "required field" error naming that field: pass it explicitly, or (for the growth/return/sale-price field) pass the string "market" for the S&P 500 trailing average; never invent a number. The covered-tickers resource (resources/list) lists which symbols resolve growth.
horizonYesPlanning horizon in years (1..10). The optimizer searches all feasible per-year share allocations across this many years. The user's choice, not a modelling detail, and it changes the answer: use the value they gave, and if they gave none, ask for it rather than assuming one.
grantDateYesISO grant date (YYYY-MM-DD). Drives the 10-year statutory grant expiration (IRC §422) and the 2-year qualifying-disposition threshold from grant.
stateCodeYesTwo-letter US state code (e.g. CA, NY, TX). Drives state ordinary brackets, state long-term capital gains (LTCG) treatment, and state AMT (CA, CO, CT, MN).
volatilityNoAnnualized volatility (sigma) of the stock as a decimal (0.72 = 72%). Pass the volatility itself, not a pre-computed drag: the tool derives the horizon-cumulative drag internally, and the correct formula is horizon-dependent. This value must come from the user or from a `ticker` that resolves it as of the last market close; if neither supplies it, ask the user rather than estimating one.
filingStatusYesFederal filing status. Drives the ordinary-bracket walk, the AMT exemption tier ($90,100 single / $140,200 MFJ for 2026), and the AMT exemption phaseout start ($500,000 single / $1,000,000 MFJ).
cashReturnRateNoAnnual after-tax return on idle cash (decimal), used to time-value the cash-tax stream. 0.05 = 5% (~short-Treasury yield). Optional: defaults to 0.04 (4%, a short-Treasury-like after-tax yield) when omitted, and an explicit value overrides that default. At 0 the math collapses to a nominal sum.
expectedGrowthNoAnnual expected stock growth as a decimal (0.10 = 10%), or the string "market" to use the S&P 500 trailing average when the user has no view. Required unless `ticker` resolves it from trailing CAGR. This tool has no default for it: a value not stated by the user, not resolved by a covered `ticker`, and not the "market" sentinel is outside the input contract.
hasLeftCompanyYesTrue if the user has separated from the company. Activates the 90-day post-termination ISO exercise window measured from terminationDate.
ordinaryIncomeYesAnnual ordinary income before this exercise, USD. Baseline for the bracket walk and the AMT exemption phaseout. Must come from the user. This is taxable income after deductions, not gross wages: the engine applies no standard or itemized deduction to it.
volatilityDragNoAlternative to `volatility`: the multiplicative price haircut already computed for the planning horizon. Supply this OR `volatility` (if both are given, volatilityDrag wins). This field is for a drag figure that already exists from a prior computation; the drag formula is horizon-dependent, so a figure derived for a different horizon does not carry over. Supplying `volatility` instead lets the tool derive it.
terminationDateNoSeparation date (YYYY-MM-DD). Required only when hasLeftCompany=true (it drives the 90-day exercise-window deadline); omit it or pass null when still employed. No longer in `required` so the common employed case needs no placeholder.
carryforwardCreditNoExisting federal AMT credit (Minimum Tax Credit, Form 8801) carryforward from prior tax years, USD. Recoverable in future years where regular federal tax exceeds tentative minimum tax. Optional; defaults to 0, which is correct for most first-time exercisers. Only a prior-year AMT credit makes it non-zero.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
timingYesTiming constraints derived from grantDate and (when departed) terminationDate.
schedulesYesThe three candidate exercise schedules, each evaluated at the effective horizon. Their nfv values are directly comparable; optimized is the highest-NFV schedule the optimizer found.
stateHasAmtYesTrue when the user state levies its own AMT (CA, CO, CT, MN).
alreadyInAmtYesTrue when the user owes AMT even with zero exercise (regular tax below tentative minimum tax at baseline income).
bargainPerShareYesYear-1 bargain element per share in dollars: max(0, fmv - strike).
crossoverSharesYesMaximum whole shares exercisable in year 1 before federal AMT exceeds regular tax (the AMT crossover).
crossoverBargainYesBargain element in dollars at the crossover share count: crossoverShares x (fmv - strike).
effectiveHorizonYesHorizon actually used by the schedules: min(requested horizon, timing.maxHorizon).
departedRecommendationNoPresent only when hasLeftCompany=true and the 90-day post-termination window is still open: the partial-exercise quantity with the highest expected after-tax value found by a scan over candidate share counts, which can land a few shares off the exact optimum.

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnlyHint, idempotentHint, destructiveHint, openWorldHint=false): discloses pure deterministic computation, no network access, no PII retention, compiled-in 50-state tax tables. Most valuable, it discloses a genuine limitation — departedRecommendation is scanned not exhaustively searched and can land a few shares off optimum — plus the provenance caveat that syntactically valid numbers pass without check. No contradiction with annotations; the description reinforces, rather than repeats, the read-only/idempotent safety profile.

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

Conciseness4/5

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

The description is dense but front-loaded with the core use cases and routing before the NFV mechanics. Nearly every sentence earns its place given the 16-param financial complexity, but there is measurable redundancy: the 'market' sentinel rule appears three times (description, ticker param, expectedGrowth param) and the verification link twice. Tightening would help, but the prioritization of routing and limitations is sound.

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

Completeness5/5

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

Given 16 parameters, 2 enums, multiple resolution modes, and AMT/ISO tax complexity, this is exceptionally complete. It names the headline output (schedules.optimized.nfv), the baseline comparison plans, and the auxiliary returns, which is appropriate even with an output schema present. It covers resolution rules, the post-termination window, grant expiration, and the multi-position independence caveat — nothing an agent needs to call it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100% so baseline is 3, but the description adds cross-parameter semantics the schema alone can't convey: the three-source resolution rule for growth/volatility (explicit value, covered ticker, or 'market' sentinel), the fact neither field has a default, the volatilityDrag-OR-volatility precedence rule, and the 'number from any other source is accepted as-is' caveat. The one omission: the description explains expectedGrowth resolution but the interplay with volatilityDrag is only implied.

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

Purpose5/5

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

States a precise verb+resource: computes the multi-year ISO exercise schedule that maximizes after-tax Net Final Value (NFV). It defines NFV explicitly and names three sibling tools with the exact condition that selects each (nso_calculate for NSOs, rsu_sell_vs_hold for RSUs at vest, qsbs_check for §1202), which unambiguously differentiates it from the sibling set shown.

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

Usage Guidelines5/5

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

Opens with an exhaustive when-to-use list of user intents (AMT bomb, phantom income, early exercise, multi-year schedule) and explicitly routes away from siblings. It also gives a concrete example call, tells the agent to ask rather than assume when values are absent, and specifies the only three valid sources for growth/volatility.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0
Disambiguation4/5

Most tools are cleanly scoped to distinct instruments and decisions (ISO/AMT, NSO, RSU vest, lot selection, hedge pricing, QSBS, concentration, cash funding), and the descriptions actively cross-reference the correct tool for each scenario. The main ambiguity is among the divestment-oriented tools (rsu_lot_optimize, equity_funding_plan, concentration_analyze), though the descriptions explain their different triggers well.

Naming Consistency4/5

Names mostly follow a readable `{domain}_{action}` snake_case pattern, e.g., amt_iso_optimize, nso_calculate, qsbs_check. The verbs vary across optimize/calculate/check/analyze/plan/sell, and equity_funding_plan and protective_put_price read more as noun phrases, so the convention is recognizable but not perfectly uniform.

Tool Count5/5

With 8 tools, the set is well-scoped and each tool covers a meaningful, non-redundant computation in the equity-compensation planning domain. There are no filler tools or extreme over- nor under-provisioning.

Completeness4/5

The core single-position workflows are covered: ISO/AMT optimization, NSO exercise, RSU vest decisions, lot selection, hedging, QSBS qualification, concentration, and goal-based funding. Missing pieces are mostly edge-domain items like ESPP, disqualifying dispositions, and integrated multi-position scenarios, which are explicitly noted as out of scope or beta.