Skip to main content
Glama

QuantCalc Retirement Engine

Run a retirement projection

run_retirement_projection
Read-only

Runs a Monte Carlo retirement projection on the QuantCalc engine and returns the success rate, the ending-portfolio distribution, and the assumptions that produced them. The result states the return model that ran, the number of paths, and the income assumptions it used, including when there are none. Income tax is not modelled by this tool; run_tax_aware_projection models it.

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": {
      "current_age": "<current_age>",
      "current_savings": "<current_savings>",
      "annual_spending": "<annual_spending>"
    },
    "name": "run_retirement_projection"
  }
}

Input Schema

NameRequiredDescriptionDefault
pensionNoYearly pension income. Default 0.
allocationsNoPercentages summing to 100: [US stocks, international stocks, bonds, real estate, cash]. Default [60,10,25,5,0].
current_ageYesCurrent age of the primary person.
bucket_yearsNoOnly with withdrawal_strategy bucket: years of spending held in the cash bucket, 1-10.
return_modelNoHow returns are generated. parametric (default): the forward-looking published assumptions. bootstrap (stationary block bootstrap of historical months) and historical (real months from 1926 replayed in order) can be requested, but on this connection the engine runs parametric instead and the result says so.
ss_start_ageNoAge Social Security starts. Default 67.
inflation_rateNoAnnual inflation as a percent, e.g. 2.5. Default 2.5.
retirement_ageNoAge work income stops. Defaults to current age.
returns_sourceNoWhich published return set to use (see list_return_assumption_sources). Default jpmorgan.
annual_spendingYesPlanned yearly spending in today's dollars, before income tax (this tool runs the standard engine, which does not model tax).
current_savingsYesTotal invested portfolio today, in dollars.
life_expectancyNoAge the plan must last until. Default 92.
social_securityNoYearly Social Security in today's dollars. Default 0 — and 0 is reported as an explicit assumption, not hidden.
pension_start_ageNoAge the pension starts. Default 65.
spending_confidenceNoThe success rate the 'sustainable spending' answer is solved at: the most this plan can spend each year and still succeed on at least this percentage of paths, with the same answer if every balance were 20% lower or higher today. One of 75, 80, 85, 90, 95. Default 90.
withdrawal_strategyNoSpending rule. fixed (default): the planned amount, inflation-adjusted, every year. guyton-klinger: guardrails that cut or raise spending as the portfolio moves. vpw: variable percentage withdrawal. bucket: a cash reserve of bucket_years of spending.
monthly_contributionNoMonthly savings until retirement. Default 0.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / return_model / description
      Previous value: -"How returns are generated. parametric (default): the forward-looking published assumptions. bootstrap: stationary block bootstrap of historical months. historical: replays real months from 1926 in order. The last two need a PRO licence; without one the engine runs parametric and the result says so."New value: +"How returns are generated. parametric (default): the forward-looking published assumptions. bootstrap (stationary block bootstrap of historical months) and historical (real months from 1926 replayed in order) can be requested, but on this connection the engine runs parametric instead and the result says so."
  2. Changed1 schema field changed
    • addedInput schema / properties / spending_confidence
      Added value: +{
      +  "description": "The success rate the 'sustainable spending' answer is solved at: the most this plan can spend each year and still succeed on at least this percentage of paths, with the same answer if every balance were 20% lower or higher today. One of 75, 80, 85, 90, 95. Default 90.",
      +  "enum": [
      +    75,
      +    80,
      +    85,
      +    90,
      +    95
      +  ],
      +  "type": "integer"
      +}
  3. Changed3 schema fields changed
    • addedInput schema / properties / bucket_years
      Added value: +{
      +  "description": "Only with withdrawal_strategy bucket: years of spending held in the cash bucket, 1-10.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / return_model
      Added value: +{
      +  "description": "How returns are generated. parametric (default): the forward-looking published assumptions. bootstrap: stationary block bootstrap of historical months. historical: replays real months from 1926 in order. The last two need a PRO licence; without one the engine runs parametric and the result says so.",
      +  "enum": [
      +    "parametric",
      +    "bootstrap",
      +    "historical"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / withdrawal_strategy
      Added value: +{
      +  "description": "Spending rule. fixed (default): the planned amount, inflation-adjusted, every year. guyton-klinger: guardrails that cut or raise spending as the portfolio moves. vpw: variable percentage withdrawal. bucket: a cash reserve of bucket_years of spending.",
      +  "enum": [
      +    "fixed",
      +    "guyton-klinger",
      +    "vpw",
      +    "bucket"
      +  ],
      +  "type": "string"
      +}
  4. Changed1 schema field changed
    • changedInput schema / properties / annual_spending / description
      Previous value: -"Planned yearly spending in today's dollars."New value: +"Planned yearly spending in today's dollars, before income tax (this tool runs the standard engine, which does not model tax)."
  5. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond readOnlyHint/openWorldHint, it discloses a real behavioral caveat: bootstrap and historical may be requested but the engine runs parametric and the result says so. It also states tax is not modelled and that assumptions (including zero income) are echoed in the result. It stops short of runtime, determinism, or failure-mode expectations for a heavy simulation, so a 4 rather than 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.

Conciseness5/5

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

Three sentences, front-loaded with what runs and what comes back, then the tax boundary, then the sibling handoff. No filler and no repetition of the title.

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

Completeness4/5

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

With 17 parameters and no output schema, the description correctly spends its space describing the return payload (success rate, distribution, echoed assumptions) and the tax boundary. The remaining gap is operational: nothing about expected compute time or how an invalid allocation/withdrawal_strategy combination is reported.

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 schema already carries most parameter meaning. The description still adds value by framing annual_spending as pre-tax under the standard engine and by reinforcing that return_model requests may be silently downgraded. The spending_confidence robustness claim adds a little more, though most field-level detail lives in the schema.

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 specific verb and method ("Runs a Monte Carlo retirement projection on the QuantCalc engine") plus the concrete artifacts returned (success rate, ending-portfolio distribution, assumptions). It immediately separates itself from run_tax_aware_projection, so an agent can route between the two without opening either schema.

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?

Names the exact condition that selects the sibling instead: "Income tax is not modelled by this tool; run_tax_aware_projection models it." It also points to list_return_assumption_sources for the returns_source input, giving both an exclusion and a next step.

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.