DecisionsCalc calculators

canada can i retire

canada_can_i_retire

Read-only

Canada: can I retire at 60 with $500k (or any age and pot)? Year by year to 95 for one person or a couple: RRSP contributions until retirement, RRSP to RRIF (by 71) with the RRIF minimum withdrawal, CPP from the chosen age (−0.6%/month before 65, +0.7% after), OAS from 65-70 (years in Canada / 40, +0.6%/month deferred, +10% at 75) with the 15% recovery tax over $95,323, GIS on last year’s income, pension income splitting, an optional UK State Pension (frozen in Canada), and federal plus provincial tax for every province and territory except Quebec (2026 amounts). 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": "canada_can_i_retire"
  }
}

Input Schema

Name	Required	Description
`age`	No	Your age now
`growth`	No	Pension growth % a year after charges (an assumption)
`salary`	No	Gross pay a year, CAD
`savings`	No	Savings and investments outside pensions, CAD
`oasYears`	No	Years lived in Canada after 18 (40 = full OAS)
`province`	No	Province or territory code (Quebec not supported)
`spending`	Yes	Household spending a year in retirement after tax, today’s money, CAD
`dbFromAge`	No	Age the DB pension starts
`dbPension`	No	Defined benefit pension a year, CAD (0 if none)
`household`	No	Household
`inflation`	No	Inflation % a year
`retireAge`	Yes	Age you stop work
`contribPct`	No	Your pension contributions, % of pay
`partnerAge`	No	Partner age now
`pensionPot`	No	Pension pots today, CAD
`savingsAdd`	No	Added to savings each year until retirement, CAD
`cppStartAge`	No	Age CPP starts, 60-70
`employerPct`	No	Employer contributions, % of pay
`oasStartAge`	No	Age OAS starts, 65-70
`partnerSalary`	No	Partner gross pay a year, CAD
`cppAt65Monthly`	No	CPP estimate at 65, a month (max $1,507.65 in 2026)
`ukPensionWeekly`	No	UK State Pension forecast a week in pounds (frozen in Canada; 0 if none)
`partnerRetireAge`	No	Partner retirement age
`partnerPensionPot`	No	Partner pension pots, CAD

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds substantive modelling context instead — CPP actuarial adjustments, RRIF minimum withdrawals by 71, OAS clawback threshold, UK pension freezing, and the assumption set being in today's money. It does not say what defaults apply to the 22 optional parameters or how sensitive results are to omitted inputs, which is the main remaining behavioural gap.

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 question the tool answers, then the modelling rules, then the return values — a sensible order for a complex tool. The middle is a dense laundry list of rules that is justified by the modelling depth but could be trimmed where it overlaps with the 100%-covered schema descriptions.

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?

With 24 parameters and no output schema, the description carries the return-value burden and does so explicitly: the age the money lasts to, bridge years, wealth at retirement, sustainable spending to 95, a 60/62/65 comparison, and key years in today's money. Scope limits (Quebec excluded, 2026 amounts, one or two people) are all stated, leaving nothing essential an agent needs before calling it.

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 above that by explaining the rules behind key parameters — the −0.6%/month CPP reduction before 65 and +0.7% after, the 40-years-in-Canada OAS divisor, the 15% recovery tax over $95,323, and the frozen UK State Pension. It does not tie these rules back to parameter names such as cppStartAge or oasStartAge, so the mapping is still left partly to inference.

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 and resource — modelling whether you can retire in Canada at a given age with a given pot — and immediately differentiates itself from the australia/ireland/uk `can_i_retire` siblings by naming Canada-specific mechanics (RRSP, RRIF, CPP, OAS, GIS, provincial tax excluding Quebec). An agent can pick this over the other country variants without opening any 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?

Usage context is clear: age 60 with $500k, or any age and pot, for a single person or a couple, projected year by year to 95. It also states the exclusion of Quebec and notes the amounts are 2026. It stops short of explicitly routing the agent ('for the UK use uk_can_i_retire'), relying on the country prefix and sibling names instead.

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.