LunaTerminal

Retirement plan (Monte Carlo)

retirement_plan

Read-onlyIdempotent

Run a retirement Monte Carlo simulation in today's dollars: probability that savings last through the planning age, the range of portfolio values at retirement and at the end, median depletion age when paths fail, the initial withdrawal rate, the effect of three levers (save more, retire two years later, spend 10% less) and the highest spending that keeps the target success rate. Required: currentAge, retirementAge, planToAge, savings and spending. Return and volatility default to afa's capital market assumptions for the chosen model (a step more conservative in retirement); other optional inputs default to 0, and inflation to 2.5%. Results are hypothetical.

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>",
      "planToAge": "<planToAge>",
      "savings": "<savings>",
      "spending": "<spending>"
    },
    "name": "retirement_plan"
  }
}

Input Schema

Name	Required	Description
`seed`	No	Random seed; the same inputs and seed give the same result (default 1).
`model`	No	Model portfolio used for omitted return and volatility inputs: conservative (20% stocks), moderately_conservative (40% stocks), moderate (60% stocks), growth (75% stocks), aggressive (90% stocks). Default moderate.
`trials`	No	Number of simulated market paths (default 2000).
`savings`	Yes	Current investable savings.
`spending`	Yes	Annual retirement spending from the portfolio and other income, in today’s dollars.
`inflation`	No	Inflation (%).
`planToAge`	Yes	Plan through age.
`currentAge`	Yes	Current age.
`volatility`	No	Annual volatility before retirement (%).
`otherIncome`	No	Social Security, pensions and other income per year, in today’s dollars.
`contribution`	No	Annual savings until retirement.
`distribution`	No	normal (default) or fat-tailed returns (Student-t), which make severe years more frequent.
`retirementAge`	Yes	Retirement age.
`targetSuccess`	No	Success rate in percent used for sustainable spending (default 85).
`expectedReturn`	No	Expected annual return before retirement (%).
`otherIncomeAge`	No	Age other income starts.
`volatilityRetired`	No	Annual volatility in retirement (%).
`withdrawalTaxRate`	No	Average tax rate on withdrawals in percent; withdrawals are grossed up for it (default 0).
`contributionGrowth`	No	Annual savings growth above inflation (%).
`expectedReturnRetired`	No	Expected annual return in retirement (%).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover the safety profile (read-only, idempotent, closed-world, non-destructive), so the description's additional value is in assumption disclosure: return/volatility default to the chosen model's capital market assumptions, being 'a step more conservative in retirement', other optional inputs default to 0, inflation to 2.5%, and results are hypothetical. It stops short of stating trial-count limits, runtime, or failure modes, but adds genuine context beyond annotations.

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?

Front-loaded with the verb and the simulation's outputs, then requirements, then defaults, then the hypothetical disclaimer — a sensible ordering. It is dense and long, but every clause carries information; no filler sentences.

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

Completeness3/5

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

With no output schema, the enumerated result metrics are essential and present, and required inputs plus key defaults are covered. However, for a 20-parameter tool the description accounts for only 5 required and 3 defaulted inputs, leaving settings like otherIncome/otherIncomeAge, contributionGrowth, withdrawalTaxRate, distribution (fat tails), and targetSuccess unexplained in prose — an agent must read the schema for the levers that materially change results.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already explains all 20 parameters, including the model enum, seed reproducibility, and trial bounds. The description adds only marginal material: the default inflation of 2.5% (not stated in the schema's inflation field) and the retirement-phase conservatism step. Restating the five required inputs duplicates the schema's required array, and the remaining ~15 optional parameters are not mentioned at all.

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?

Specific verb ('Run a retirement Monte Carlo simulation') plus an enumerated result set: success probability, portfolio value range, median depletion age, initial withdrawal rate, three levers, and sustainable spending. That result list cleanly distinguishes it from siblings like inherited_ira_plan, roth_conversion_plan, and rebalance_plan, which are different planning exercises.

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

Usage Guidelines3/5

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

Usage is implied by the enumerated outputs and the lever set ('save more, retire two years later, spend 10% less'), so an agent can infer this is the scenario-simulation tool. But there is no explicit when-to-use/when-not, no mention of when a simpler deterministic projection or a sibling planner would be preferred, and no prerequisites stated.

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

All LunaTerminal tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?