Skip to main content
Glama

PoliErgaleio

run_retirement_stress_test

Runs a deterministic projection plus Monte Carlo simulation of a retirement savings plan. Seeded market and medical paths use independent random streams. Age-keyed returnOverrides replace returns in both calculation modes; nonDepletionProbability always reports basic no-shortfall success, while successProbability also applies supplied successCriteria. Use for a retirement savings sustainability or portfolio-longevity projection. Reuse the user's ages, savings, contributions and planned monthly spending; ask for each missing essential input and never use example personal values. Values are EUR, contributions/drawdown are monthly, and ages are years. Supply pensionStreams to include Cyprus or foreign pension income; concurrent streams are aggregated before applying personal tax allowances and the shared €180,000 GESY ceiling. Foreign pensions use the 2026 flat 5% rate above €5,000 unless a net override is supplied. Omitted state pension means pension income is excluded. accumulationVolatility and distributionVolatility set annual return volatility; medicalShocks optionally models acute and long-term-care costs. returnOverrides replaces age-specific returns in both calculation paths. Market and medical random streams are independent, so changing medical assumptions does not shift seeded market paths. successCriteria optionally sets nominal retirement and terminal thresholds. nonDepletionProbability reports basic no-shortfall success separately. Runs without seed are stochastic; a supplied seed makes identical inputs repeatable for the same implementation version.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "currentAge": "<currentAge>",
      "retirementAge": "<retirementAge>",
      "currentSavings": "<currentSavings>",
      "monthlyContribution": "<monthlyContribution>",
      "monthlyDrawdown": "<monthlyDrawdown>"
    },
    "name": "run_retirement_stress_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoOptional unsigned 32-bit seed for repeatable runs with identical inputs and implementation versions. Omit to keep the run stochastic.
endAgeNoPlanning horizon age (default 90).
currentAgeYesAge today.
simulationsNoMonte Carlo runs (default 1000).
statePensionNoExpected monthly state pension in EUR.
inflationRateNoAnnual percentage value (e.g. 2.5 for 2.5%). Supply the actual rate unless the user accepts a stated modelling default.
medicalShocksNoOptional acute-medical and long-term-care sampling assumptions. Medical and market paths are seeded independently.
retirementAgeYesPlanned retirement age.
currentSavingsYesCurrent investable savings balance in EUR.
pensionStreamsNoOptional annual pension streams that offset retirement drawdown. Concurrent streams are aggregated before applying progressive tax, the single 2026 foreign-pension €5,000 allowance, and the shared personal GESY ceiling. A supplied netAnnualOverride is treated as already net and is used as-is.
monthlyDrawdownYesPlanned monthly withdrawal in retirement in EUR.
returnOverridesNoOptional age-keyed replacement annual nominal return percentages. Each listed age replaces its simulated and deterministic return; the market draw is still consumed so later seeded years remain aligned.
successCriteriaNoOptional nominal thresholds that make success stricter than basic non-depletion.
monthlyContributionYesMonthly contribution until retirement in EUR.
expectedAnnualReturnNoAnnual percentage value (e.g. 2.5 for 2.5%). Supply the actual rate unless the user accepts a stated modelling default.
accumulationVolatilityNoAnnual accumulation return volatility in percentage points.
distributionVolatilityNoAnnual retirement return volatility in percentage points.
expectedAnnualReturnRetirementNoAnnual percentage value (e.g. 2.5 for 2.5%). Supply the actual rate unless the user accepts a stated modelling default.

Output Schema

NameRequiredDescriptionDefault
seriesNo
ltcRunRateYes
assumptionsYes
acuteRunRateYes
shockRunRateYes
medianDepletionAgeYes
successProbabilityYes
averageDepletionAgeYes
medianTerminalWealthYes
nonDepletionProbabilityYes
deterministicFinalBalanceYes
worstCase10thPercentileBalanceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / accumulationVolatility
      Added value: +{
      +  "default": 15,
      +  "description": "Annual accumulation return volatility in percentage points.",
      +  "maximum": 50,
      +  "minimum": 1,
      +  "type": "number"
      +}
    • addedInput schema / properties / distributionVolatility
      Added value: +{
      +  "default": 10,
      +  "description": "Annual retirement return volatility in percentage points.",
      +  "maximum": 50,
      +  "minimum": 1,
      +  "type": "number"
      +}
    • addedInput schema / properties / medicalShocks
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Optional acute-medical and long-term-care sampling assumptions. Medical and market paths are seeded independently.",
      +  "properties": {
      +    "acuteEnabled": {
      +      "default": false,
      +      "type": "boolean"
      +    },
      +    "acuteEndProbPct": {
      +      "default": 9,
      +      "maximum": 100,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "acuteSevereCost": {
      +      "default": 25000,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "acuteStartProbPct": {
      +      "default": 2,
      +      "maximum": 100,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "acuteTypicalCost": {
      +      "default": 4000,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "ltcAnnualCost": {
      +      "default": 18000,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "ltcEnabled": {
      +      "default": false,
      +      "type": "boolean"
      +    },
      +    "ltcEntryCost": {
      +      "default": 6000,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "ltcLifetimeProbPct": {
      +      "default": 25,
      +      "maximum": 100,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "ltcMaxYears": {
      +      "default": 4,
      +      "minimum": 1,
      +      "type": [
      +        "integer",
      +        "null"
      +      ]
      +    },
      +    "ltcStartAge": {
      +      "default": 80,
      +      "minimum": 0,
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "acuteEnabled",
      +    "acuteStartProbPct",
      +    "acuteEndProbPct",
      +    "acuteTypicalCost",
      +    "acuteSevereCost",
      +    "ltcEnabled",
      +    "ltcStartAge",
      +    "ltcLifetimeProbPct",
      +    "ltcEntryCost",
      +    "ltcAnnualCost",
      +    "ltcMaxYears"
      +  ],
      +  "type": "object"
      +}
    • addedInput schema / properties / returnOverrides
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Optional age-keyed replacement annual nominal return percentages. Each listed age replaces its simulated and deterministic return; the market draw is still consumed so later seeded years remain aligned.",
      +  "patternProperties": {
      +    "^\\d{1,3}$": {
      +      "description": "Replacement annual return percentage at this age.",
      +      "type": "number"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / successCriteria
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Optional nominal thresholds that make success stricter than basic non-depletion.",
      +  "properties": {
      +    "retirementHurdleNominal": {
      +      "description": "Minimum nominal balance required at retirement age, EUR.",
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "terminalFloorNominal": {
      +      "description": "Minimum nominal balance required at endAge, EUR.",
      +      "minimum": 0,
      +      "type": "number"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedOutput schema / properties / nonDepletionProbability
      Added value: +{
      +  "type": "number"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "successProbability",
      -  "medianDepletionAge",
      -  "averageDepletionAge",
      -  "deterministicFinalBalance",
      -  "worstCase10thPercentileBalance",
      -  "medianTerminalWealth",
      -  "shockRunRate",
      -  "acuteRunRate",
      -  "ltcRunRate",
      -  "assumptions"
      -]New value: +[
      +  "successProbability",
      +  "nonDepletionProbability",
      +  "medianDepletionAge",
      +  "averageDepletionAge",
      +  "deterministicFinalBalance",
      +  "worstCase10thPercentileBalance",
      +  "medianTerminalWealth",
      +  "shockRunRate",
      +  "acuteRunRate",
      +  "ltcRunRate",
      +  "assumptions"
      +]
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does it well: it discloses determinism versus stochasticity with a seed, independent seeded market/medical streams, that changing medical assumptions does not shift market paths, the tax and GESY-ceiling aggregation order for pension streams, the 2026 flat 5% foreign-pension rate, and that omitting statePension excludes pension income entirely. It also distinguishes nonDepletionProbability (basic no-shortfall) from successProbability (applies successCriteria), which is genuinely useful behavioral nuance.

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

Conciseness3/5

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

The purpose is front-loaded, but the paragraph is long and repeats itself: returnOverrides replacing returns in both modes is stated twice, 'market and medical streams are independent' appears twice, and the nonDepletionProbability no-shortfall explanation is duplicated. The repetition costs space that could have gone to the unaddressed gaps.

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?

For an 18-parameter tool with nested objects, the definition covers the concepts an agent needs: units, seeding, volatility inputs, medical shock modelling, pension stream tax treatment, and success criteria versus basic depletion. An output schema exists, so return-value documentation is not required, and nothing essential to calling 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 the baseline is 3, and the description adds real cross-parameter meaning: units (EUR, monthly contributions/drawdown, ages in years), that returnOverrides replaces returns in both calculation paths while the market draw is still consumed, that concurrent pension streams are aggregated before tax, and that netAnnualOverride is used as-is. These are interactions the schema alone does not convey.

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

Purpose5/5

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

The first sentence names a specific verb and resource — a deterministic projection plus Monte Carlo simulation of a retirement savings plan — and the later 'Use for a retirement savings sustainability or portfolio-longevity projection' pins the domain. An agent can distinguish this from siblings like calculate_cyprus_state_pension or analyze_portfolio 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.

Usage Guidelines4/5

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

It gives clear trigger conditions ('Use for a retirement savings sustainability or portfolio-longevity projection') and strong operational guidance: reuse the user's ages, savings, contributions and planned monthly spending, ask for each missing essential input, and never use example personal values. It does not name a sibling alternative or an explicit when-not-to-use case, so it stops short of a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources