DecisionsCalc calculators

uk can i retire

uk_can_i_retire

Read-only

UK: can I retire at 60 with £300k (or any age and pot)? Year by year to 95 for one person or a couple, on the 2027-28 rules after Budget 2026: pay and pension contributions until retirement, pots drawn from the normal minimum pension age (55, 57 from 6 April 2028) with 25% tax-free cash within the £268,275 Lump Sum Allowance and the rest drawn as taxable income, defined benefit pensions, the new State Pension from the State Pension age by date of birth (full £250.70 a week from April 2027), savings, a spending target in today’s money, and income tax (personal allowance tapered over £100,000; England/Wales/NI or Scottish bands, frozen to 2030-31) and National Insurance on pay. Growth and inflation are assumptions. Returns the age the money lasts to, bridge years, wealth at retirement, the spending that lasts to 95, a retire-at-60/62/65 comparison and key years in today’s money.

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": {
      "retireAge": "<retireAge>",
      "spending": "<spending>"
    },
    "name": "uk_can_i_retire"
  }
}

Input Schema

Name	Required	Description
`growth`	No	Pension growth % a year after charges (an assumption)
`salary`	No	Gross pay a year, GBP
`savings`	No	Savings and investments outside pensions, GBP
`scotland`	No	Scottish taxpayer
`spending`	Yes	Household spending a year in retirement after tax, today’s money, GBP
`birthYear`	No	Year of birth (sets the State Pension age)
`dbFromAge`	No	Age the DB pension starts
`dbPension`	No	Defined benefit pension a year, GBP (0 if none)
`household`	No	Household
`inflation`	No	Inflation % a year
`retireAge`	Yes	Age you stop work
`birthMonth`	No	Month of birth 1-12 (matters for April 1960 - March 1961 and April 1977 - March 1978)
`contribPct`	No	Your pension contributions, % of pay
`partnerAge`	No	Partner age now
`pensionPot`	No	Pension pots today, GBP
`savingsAdd`	No	Added to savings each year until retirement, GBP
`employerPct`	No	Employer contributions, % of pay
`partnerSalary`	No	Partner gross pay a year, GBP
`partnerBirthYear`	No	Partner year of birth
`partnerRetireAge`	No	Partner retirement age
`partnerPensionPot`	No	Partner pension pots, GBP
`statePensionWeekly`	No	Expected State Pension a week, GBP (full new State Pension £250.70 from April 2027; 0 if none)

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real behavioural context — the statutory rules baked in (NMPA 55 rising to 57 in April 2028, £268,275 LSA, tapered personal allowance, frozen bands to 2030-31) and the admission that growth and inflation are user assumptions rather than facts. It stops short of saying what happens with the 20 optional parameters left at defaults.

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 scenario question is well front-loaded, but the remainder is a single run-on sentence that stacks a dozen modelling assumptions into one breath, making it hard to scan. Nearly every clause carries information, yet the lack of sentence breaks or grouping costs readability.

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?

For a 22-parameter projection tool with no output schema, the description does the necessary work: it spells out the modelled rules and explicitly lists the return values (age the money lasts to, bridge years, wealth at retirement, spending that lasts to 95, retire-at-60/62/65 comparison). The gap is silence on defaults for the 20 optional inputs, which materially change the projection.

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 coverage is 100%, so every one of the 22 parameters is already documented, and the description largely restates schema facts (spending in today's money, 25% tax-free cash, DB pensions, State Pension by date of birth). It does add interaction meaning — the Scotland flag selecting Scottish bands, the taper over £100,000, contributions accruing until retirement — but not enough to exceed the baseline.

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 description opens with a concrete verb-plus-resource framing ('can I retire at 60 with £300k (or any age and pot)?') and enumerates exactly what the model projects: drawdown year by year to 95 for one person or a couple under 2027-28 rules. The 'UK:' prefix and the detail set cleanly distinguish it from the sibling country variants such as ireland_can_i_retire or canada_can_i_retire.

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 establishes clear applicability: UK rules as of Budget 2026, single or couple, any retirement age and pot size, with an explicit statement that growth and inflation are assumptions. It never states exclusions or names alternatives (e.g. that non-UK residents or care-fee scenarios belong to uk_care_home_fees), so routing still relies on inference.

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

All DecisionsCalc calculators 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.