calculators

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

Annotations already declare this a non-destructive, closed-world read, so the safety profile is covered. The description adds useful scope detail by breaking out what the carrying-cost calculation includes (manager fee plus custodian margin and short rebate spreads), but with no output schema it says nothing about the shape of results — whether it returns a ranked recommendation, a year-by-year cost table, or illustrative-only figures — nor what tax assumptions underlie the comparison.

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?

Front-loading with 'Use this tool whenever' is a good structural choice, but the body is a single dense run-on sentence that packs strategy names, four extension ratios, cost components, three vendor names, and two custodians into one clause chain. It is efficient in length but costly to parse, and the extension ratios are effectively restated from the enum.

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 7-parameter read-only comparison tool with no output schema, the description covers the TALS side thoroughly and flags the 2026 data vintage, which is important for an agent reasoning about currency of results. However, the two comparison arms named in the title — direct indexing and a staged ETF sale, the latter driven by the stagedYears parameter — never appear in the description body, and no tax-rate assumptions are stated, leaving the agent unsure what the comparison actually benchmarks against.

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%, so the baseline is 3; the description climbs above it by tying extensionPct values to real-world products (AQR, Cache, Brooklyn, Neuberger Berman SMAs) and by pairing custodian choice with actual 2026 Schwab/Fidelity minimums and restrictions. It still leaves marginType ('portfolio' vs 'reg_t') effects on short rebate and margin cost unexplained, a moderate residual gap.

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 names a concrete analysis (diversifying a concentrated low-basis stock position) and enumerates the specific strategies and sub-tasks involved: TALS extension variants (130/30 through 300/200), carrying-cost computation (manager fee, custodian margin, short rebate spreads), and 2026 Schwab/Fidelity account minimums. An agent can distinguish this from the sibling SBLOC, Roth, RMD, and estate tools without opening the schema.

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 'use this tool whenever...' framing gives explicit positive triggers tied to user phrasing (advisor asks how to diversify a concentrated low-basis position, evaluates a 130/30 or 200/100 SMA, checks custodian minimums). It stops short of naming exclusions or sibling alternatives — most notably it never says to use compare_sbloc_borrow_vs_sell instead when the client's question is borrowing against the position rather than exiting it.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered and the description doesn't need to restate it. What the description adds is statutory grounding (OBBBA amounts, Rev. Rul. 2023-2, Sec. 675(4)(C) swap powers), but it says nothing about assumptions, projected-growth modeling over horizonYears, or the epistemic status of the 2027 projection.

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?

A single front-loaded sentence whose first clause is the usage trigger, with each subsequent clause earning its place as a distinct trigger. It is dense and slightly overstuffed with statutory citations, but no sentence is wasted or redundant.

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?

Seven parameters with full schema coverage and a safety annotation profile are handled, but there is no output schema and the description never says what the analysis produces — a tax liability comparison, a step-up benefit estimate, a recommendation, or just numbers. For a multi-scenario calculator, an agent cannot predict the shape or scope of the result.

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%, including enum labels and default values, so the parameters are already fully documented. The description supplies domain framing for those inputs (exemption year amounts, gift-vs-hold semantics) but adds no per-parameter detail such as how assetCostBasis interacts with appreciatedAssetValue or what horizonYears does to the projection. Baseline 3 applies.

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?

States a specific analytic job — comparing Sec. 1014 step-up in basis against Sec. 1015 carryover basis for lifetime gifting, plus federal/state estate tax exposure — with the governing statutes named. It is clearly distinguishable from siblings like calculate_roth_conversion or compare_sbloc_borrow_vs_sell, which are unrelated domains.

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?

Opens with an explicit 'use this tool whenever...' trigger list covering estate tax questions, gift-vs-hold decisions, SLAT/grantor trust questions, and state cliff states, which gives strong when-to-use context. It never states when NOT to use it or names a sibling to defer to for adjacent questions such as exemption parameter lookups (get_irs_statutory_parameters).

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered structurally. The description adds no behavioral context beyond the trigger list: it does not say what the calculation returns, what assumptions it bakes in (traditional vs. Roth balance, single-life vs. joint table selection), or that it is a deterministic calculator with no side effects. Useful for routing, thin on behavior.

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?

It is a single front-loaded sentence, which is good structure, but it is a run-on that reads as keyword stuffing with statutory citations (Final Regulations T.D. 10001, Form 5329 RC, 25% vs. 10%) packed into one clause chain. Every clause does carry some routing signal, but the density hurts scannability.

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 read-only, deterministic calculator with no output schema and a fully documented nine-parameter schema, the main thing an agent needs is knowing which question types route here, and the description covers RMD, inherited IRA, surviving spouse, QCD, and penalty waiver cases. The missing piece is any hint about the shape of the result or the assumptions behind the projection, which would matter for a multi-year tax calculator.

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 every one of the nine parameters, including the year and filing enums and the birth-year thresholds that drive applicable RMD age, is already documented in the schema. The description adds no parameter-level meaning such as how qcdAmount interacts with the taxable RMD or what spouseBirthYear triggers beyond what the schema states. Baseline 3 applies.

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 names a specific verb (calculate) and specific resources (RMD, Inherited IRA 10-year schedule, QCD savings, missed-RMD penalty waivers under SECURE 2.0 Sec. 302), which cleanly separates it from siblings like calculate_roth_conversion or analyze_estate_tax_and_stepup. It falls short of a 5 because the purpose is delivered as a comma-spliced trigger list rather than a single clear statement of what the tool computes.

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?

It gives explicit activation guidance — 'Use this tool whenever a user asks to calculate their RMD for 2025, 2026, or 2027' — and implicitly bounds scope to those three years. There is no when-not guidance and no sibling is named as the alternative for adjacent questions such as Roth conversions, which keeps it from a 5.

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

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

Annotations already establish readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds no behavioral context beyond that: it never says what the calculation returns, whether it is deterministic against a fixed statutory year, or which tax-year parameters it assumes. For a planning calculator with no output schema, that leaves the agent guessing at the response shape.

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?

It is a single sentence, front-loaded with the trigger phrase and packed with the four qualifying scenarios, with no filler or repetition. The density makes it slightly harder to scan than a short bulleted trigger list would be, but nothing is wasted.

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?

Seven parameters, two of them required, are fully documented in the schema, so input completeness is fine. The gap is on the output side: with no output schema, the description should say what comes back (tax cost, bracket headroom, IRMAA surcharge, pro-rata taxable fraction) and it does not. For a multi-scenario financial calculator, that is a meaningful omission.

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%, and the schema itself explains IRA basis, Form 8606 provenance, the IRMAA lookback at 63+, and the OBBBA Senior Deduction at 65+. The description adds no further parameter meaning, so the baseline 3 for a fully documented schema is appropriate.

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 names a concrete verb-and-resource pairing (convert Traditional/Rollover IRA to Roth and calculate the tax cost) plus three specific modeling capabilities: bracket/IRMAA cliff ceilings, the Sec. 408(d)(2) pro-rata rule, and the Mega Backdoor 401(k). That is far more specific than a title restatement. It does not, however, contrast itself with siblings like calculate_rmd_and_tax_cliffs or simulate_form_1040_and_bracket_room, which overlap on the bracket-room modeling.

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 phrase 'Use this tool whenever a user asks...' enumerates four concrete trigger scenarios (conversion sizing, cliff avoidance, backdoor pro-rata, mega backdoor), which gives an agent a clear entry condition. There is no explicit when-not guidance or named alternative for adjacent questions like RMD cliffs or straight 1040 simulation.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered and the bar is lower. The description contributes domain behavior by surfacing the Line 4 prior-distribution reduction and the AGI-unlock mechanic, telling the agent the calculation is stateful with respect to distributions and deductions. It says nothing about what is returned (credit rate tier, dollar amount, match amount) or about eligibility caveats like the 18+ age rule, which remains buried in the schema.

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?

A single front-loaded sentence with the trigger first and the specific statutes/forms enumerated after; no filler or repetition. It is dense but every clause names a distinct covered scenario, so little is wasted.

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?

With eight parameters, two enums, and no output schema, the definition covers the input side adequately via the schema but leaves the return side entirely unspecified — an agent cannot tell whether it gets a credit amount, a rate tier, a match amount, or all three. Given read-only annotations and full schema coverage, a 3 is a fair minimum-viable rating rather than a serious deficiency.

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 schema already documents all eight parameters including enums and defaults; baseline is 3. The description adds modest framing by tying preTax401kOrIraDeduction to AGI reduction and testingPeriodDistributions to the Line 4 rule, but it does not add format, interaction, or precedence guidance beyond that.

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?

Names the exact artifacts it handles: Form 8880 / IRC Sec. 25B Saver's Credit, the 2027 SECURE 2.0 Sec. 6433 50% Treasury match, the Line 4 distribution reduction, and AGI-lowering via pre-tax contributions. That is enough to separate it from siblings like calculate_roth_conversion or calculate_rmd_and_tax_cliffs. It never states the output as a verb+resource ('calculates X for a given taxpayer'), so it reads as a topic list rather than a description of what the tool produces.

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 explicit trigger conditions ('use this tool whenever a user asks about...') covering four concrete topic areas, which is stronger than most calculators get. It stops short of naming alternatives or when-not-to-use conditions (e.g., non-retirement credits, or the AGI-simulation sibling simulate_form_1040_and_bracket_room).

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

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

Annotations already declare readOnly=true, destructive=false, closed-world, so the safety profile is covered. The description adds real behavioral value by naming the computed outputs: tax gross-up penalty, break-even borrowing rate, IRC Sec. 163(d) Form 4952 deduction, and LTV margin-call buffer. It omits assumptions (e.g. assumed capital gains rate) and any caveats, which keeps it short of a 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 usage trigger is front-loaded in the opening clause, followed by a compact list of computed quantities. Dense but every clause carries information; the parenthetical cash-use examples are useful rather than filler.

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?

With 7 fully documented parameters and no output schema, the description does the needed work by enumerating the outputs computed. It stops short of describing the comparison result format or the tax assumptions baked in, which would matter for interpreting the break-even rate.

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 every parameter is already documented in the schema, setting the baseline at 3. The description links interestDeductible to the 163(d)/Form 4952 deduction and ties marketReturn/LTV to the margin-call buffer, adding modest conceptual framing but no new per-parameter 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?

States a specific comparison verb (sell appreciated stocks/ETFs vs. borrow via SBLOC/PAL/margin) with a concrete decision framing. It is unmistakable against siblings like calculate_roth_conversion or analyze_estate_tax_and_stepup, which address entirely different planning questions.

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?

Gives explicit trigger conditions: user needs cash liquidity for a real estate bridge, tax bill, tuition, or business investment, and asks whether to sell or borrow. It does not name when NOT to use it or point to an alternative tool, but no sibling overlaps this decision space, so the gap is minor.

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

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

The description discloses advanced behavioral traits beyond the annotations, specifically detailing the calculation of maximum 2026 employee/employer contributions and its ability to evaluate specific IRS concepts like Sec. 199A QBI and Backdoor Roth effects. This adds crucial technical depth.

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 dense single sentence, but it is perfectly structured to pack maximum value. Every phrase serves to define the scope, the calculations, or the advanced tax concepts addressed, leaving zero unnecessary 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 high complexity of the tool—which manages multiple entity types, specific IRS caps for 2026, and advanced tax strategies—the definition is extremely complete. It addresses the high-level logic that an agent would need to understand the tool's utility.

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?

Although the schema coverage is 100%, the description adds vital semantic meaning by specifying how the 'comp' and 'entity' parameters interact within the calculation. It clarifies that 'comp' can represent either W-2 wages or Schedule C net profit, which adds necessary context for the agent.

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 is highly specific, clearly defining the action (compare Solo 401k vs SEP IRA), the target audience (self-employed, LLC owners), and the primary calculative outputs. It distinguishes itself from general tax tools by focusing on optimal S-Corp W-2 salary solutions and specific contribution comparisons.

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?

It provides explicit usage guidelines by naming the persona the tool is intended for (business owners, 1099 contractors, S-Corp owners). This provides clear operational context that guides the agent to use it only when that specific user type or calculation is requested.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety and scope profile is covered by structured data. The description does add one genuinely useful behavioral fact beyond the schema: 2027 figures are projected rather than official. It discloses nothing about caching, response size, or currency of the tables, so it is solid but not rich.

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 scope list is front-loaded and every enumerated item corresponds to real coverage, so nothing is padding. The weakness is structural: the entire definition is one ~90-word sentence, which makes it a scannable keyword wall rather than prose an agent can parse quickly.

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 one-parameter, closed-world, read-only lookup with fully documented schema, the description is close to sufficient: an agent knows exactly which data domains are covered. Because there is no output schema, a short note on return shape (flat value table vs. nested by category) would have closed the remaining gap.

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% and the single enum parameter is already documented with the Official/Projected distinction. The description restates the same year values without adding format, defaulting behavior, or fallback guidance for unsupported years. Baseline 3 applies since the schema carries the parameter burden.

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 enumerates the exact datasets returned: 2025-2027 brackets, standard deduction, OBBBA Sec. 70103 Senior Deduction phase-out, 401(k)/SEP/IRA limits, IRMAA tiers, QCD/QLAC caps, RMD Table III factors, and Saver's Match thresholds. This is a highly specific resource statement. It stops short of a 5 because it never frames the tool as a read-only reference lookup as opposed to the sibling calculate_* tools, leaving the boundary implicit.

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?

A clear trigger is given: 'Use this tool whenever a user asks for official 2025, 2026, or projected 2027 ...'. That is explicit activation context. There are no exclusions and no sibling is named as an alternative (e.g., 'for computed liability use simulate_form_1040_and_bracket_room'), which keeps it out of 5 territory.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered; the description adds that this is an estimate/simulation spanning specific statutory lines (1a-38, 6b, 13a, 13b) and ceilings. It does not explicitly say results are non-authoritative planning estimates or discuss assumptions baked into defaults, which would have been valuable added context beyond the 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?

It is front-loaded with the trigger phrase, but the whole definition is one ~100-word run-on sentence with a dense comma/"or" list that is harder to scan than a short lead sentence plus bullets. Every clause is substantive, but structure costs it.

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?

With 8 parameters and no output schema, the description does the necessary work of naming what comes back (return lines, bracket room, 0% LTCG room, ACA cliff status, 8962/8995/Schedule 1-A flow-through). What is missing is an indication of whether results are single-year only and what the numeric output shape roughly is, though the absence of an output schema is partly offset by the conceptual enumeration.

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% and every parameter maps to an explicit Form 1040 line, so the schema already carries the semantics. The description adds no per-parameter meaning (e.g., how netLtcg interacts with the 0% ceiling or whether rothConversions are included in bracket room), so the baseline of 3 applies.

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?

States a specific verb+resource set (simulate a full Form 1040 estimate, remaining bracket room, 0% LTCG headroom, ACA cliff, SS/QBI/OBBBA flow-through) and enumerates the line-level outputs, so an agent can immediately tell what it produces. It is clearly differentiated from siblings like calculate_rmd_and_tax_cliffs because it is the only holistic full-return simulation.

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?

"Use this tool whenever a user asks for..." followed by five concrete trigger scenarios is unusually strong when-to-use guidance. It stops short of naming when NOT to use it or pointing to alternatives, even though bracket-room and Roth-conversion overlaps with calculate_rmd_and_tax_cliffs and calculate_roth_conversion are obvious candidates for a routing note.

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