Skip to main content
Glama

QuantCalc Retirement Engine

Compare published return assumptions

compare_return_assumptions
Read-only

Runs the same plan against several published capital market assumption sets and returns the success rate and median outcome under each, showing how far the answer moves with the return forecast used. Every input is optional: omitted plan inputs use an illustrative plan, which the reply states in its first line.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "compare_return_assumptions"
  }
}

Input Schema

NameRequiredDescriptionDefault
pensionNoYearly pension income. Default 0.
sourcesNoSource ids to compare. Defaults to all.
allocationsNoPercentages summing to 100: [US stocks, international stocks, bonds, real estate, cash]. Default [60,10,25,5,0].
current_ageNoCurrent 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_spendingNoPlanned yearly spending in today's dollars, before income tax (this tool runs the standard engine, which does not model tax).
current_savingsNoTotal 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. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
      -  "current_age",
      -  "current_savings",
      -  "annual_spending"
      -]New value: +[]
  4. 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"
      +}
  5. 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)."
  6. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description must carry the rest — and it does add real context: the reply's first line states which illustrative plan was assumed when inputs are omitted, and it describes what comes back (success rate and median outcome per assumption set). It does not mention cost/latency for a multi-scenario run or how many sources are compared by default, which are the remaining behavioral gaps.

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?

Two tight sentences with zero filler. The comparative purpose is front-loaded and the default-plan caveat follows as supporting detail, which is the right ordering.

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 18 optional parameters and no output schema, the description does the important work of describing the return shape (success rate and median outcome under each source) and the default-plan behavior. It is slightly thin on how many sources are compared when sources is omitted and on relative cost, but nothing essential to a correct call 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; the description earns a step up by explaining the omission semantics that the schema's empty required list does not convey — every input is optional and omitted plan inputs fall back to a stated illustrative plan. It adds no field-level detail beyond that, but none is needed given the rich 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 resource: runs the same plan against several published capital market assumption sets and reports success rate plus median outcome under each. The comparative framing ('showing how far the answer moves with the return forecast used') cleanly separates it from single-scenario siblings like run_retirement_projection without needing to name them.

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?

Makes the use case clear: compare outcomes across return assumption sets rather than run one plan. It also points to list_return_assumption_sources for discovering valid source ids. It stops short of explicit exclusions (e.g. 'use run_retirement_projection instead when you only need one scenario'), so the agent must infer the boundary.

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.