Verified 2026 Canadian payroll math: employer total cost, employee take-home, net-to-gross. Free.
Scored across 3 tools
Each tool targets a distinct payroll calculation: gross-to-net, gross-to-employer-cost, and net-to-gross inversion. The descriptions explicitly state the direction of calculation and the unique use case (e.g., net_to_gross for household employers), leaving no practical overlap.
All tool names use snake_case consistently and are descriptive noun phrases. However, they do not follow a uniform verb_noun pattern (e.g., employee_take_home vs net_to_gross_salary), which is a minor deviation.
Three tools precisely cover the three core calculation directions (gross→net, gross→employer cost, net→gross) without redundancy. The count is well-scoped for the server's focused purpose.
The surface covers the key payroll inversions and includes remittance details. Minor gaps exist, such as a direct tool to compute required gross from a desired employer total cost or multi-employee batch support, but these are workable around.
2026 take-home pay for a Canadian employee on regular salary: CPP/QPP (incl. second-ceiling CPP2/QPP2), EI (and QPIP for Quebec), federal and provincial income tax withheld, net pay per year and per pay period. Assumes a full-year employee with basic TD1 claims. Supported: all 13 Canadian provinces/territories.
| Name | Required | Description | Default |
|---|---|---|---|
| province | Yes | Two-letter province/territory code | |
| annual_salary | Yes | Gross annual salary, CAD | |
| pay_frequency | No | Pay frequency for the per-period view (default biweekly) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description handles transparency. Discloses deductions, assumptions, and year (2026). No side effects; it's a calculation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words. Front-loaded with purpose, then assumptions. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description explains return values (net per year and per period). Assumptions and coverage are sufficient for a calculation tool with no annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all 3 params (100%). Description adds value by connecting parameters to deductions and output frequencies, enhancing meaning beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool computes take-home pay for Canadian employees, listing specific deductions (CPP/QPP, EI, QPIP, taxes) and outputs (net per year and per period). Siblings are employer_cost and net_to_gross, making this distinct.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states assumptions (full-year employee, basic TD1 claims) and coverage (all 13 provinces). No when-not-to or alternatives, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
What a Canadian employee REALLY costs the employer for 2026: gross salary plus mandatory employer-side contributions (CPP + CPP2 + EI at 1.4x; for Quebec: QPP + QPP2 + EI + QPIP + health services fund + labour-standards contribution), with the excluded items (workers' comp, EHT, vacation pay, benefits) disclosed, never silently omitted. Supported: all 13 Canadian provinces/territories. Annual planning figures.
| Name | Required | Description | Default |
|---|---|---|---|
| province | Yes | Two-letter province/territory code where the employee works | |
| annual_salary | Yes | Gross annual salary, CAD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses what is included (CPP, EI, etc.), what is excluded (workers' comp, EHT, etc.), and that items are never silently omitted. It also specifies the year and province coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is informative and front-loaded, but slightly verbose. Each sentence contributes value, making it concise overall.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers inputs, exclusions, and scope thoroughly. However, it lacks explicit output format details (e.g., whether a single number or object is returned), which is useful given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters. The description adds context (e.g., 2026, annual planning) but does not significantly deepen understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool calculates total employer cost including mandatory contributions, specifies it's for 2026, and lists included/excluded items. It distinguishes from siblings by focusing on employer cost vs employee take-home or net-to-gross.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates use for annual planning figures and specifies supported provinces. However, it does not explicitly state when not to use or compare to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Invert payroll for 2026: start from the take-home pay you agreed with the employee ("$800/week in their pocket") and get the gross salary that delivers it, the employer's true total cost, and the per-period source-deduction remittances (CRA; split CRA vs Revenu Québec for Quebec). Built for household employers (nanny payroll) who agree on take-home pay; CRA's PDOC computes gross→net and does not cover Quebec. Supported provinces: ON, AB, BC, MB, NB, NL, NT, NS, NU, PE, QC, SK, YT.
| Name | Required | Description | Default |
|---|---|---|---|
| province | Yes | Two-letter province code | |
| pay_frequency | Yes | How often that net amount is paid | |
| target_net_pay | Yes | The agreed take-home amount per pay period, CAD |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does fairly well: it discloses the year scope (2026), the supported province set, the Quebec-specific CRA/Revenu Québec remittance split, and the three computed outputs. It never states that this is a side-effect-free calculation or describes error behavior for invalid inputs, which is the remaining gap for a no-annotation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single dense paragraph that front-loads the core action ('Invert payroll for 2026') before the use case, the competitor caveat, and the province list. Every clause contributes scope or output information, though the province enumeration in the schema's own enum makes that final sentence partly redundant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a three-parameter calculation tool with no output schema and no annotations, the description covers inputs, output set, audience, year, and geographic scope adequately. It does not describe the shape or units of the returned gross/cost/remittance figures, which would be the natural next detail given there is no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all three parameters are already documented in the schema, which sets the baseline at 3. The description adds modest interpretive value by framing target_net_pay as the agreed take-home ('$800/week in their pocket') and by noting that Quebec requires a different remittance split, but it adds no format or boundary detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource (invert payroll from net to gross) and enumerates the three outputs: gross salary, employer total cost, and source-deduction remittances. It is clearly the inverse-direction tool, but it never names or contrasts itself with the siblings employee_take_home and employer_total_cost, and its claim to also return 'the employer's true total cost' overlaps with employer_total_cost, leaving the agent to infer which to pick.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives a concrete use context ('household employers (nanny payroll) who agree on take-home pay') and names an alternative, CRA's PDOC, along with the condition that disqualifies it (PDOC computes gross→net and does not cover Quebec). It stops short of any explicit when-not-to-use guidance relative to its sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
net_to_gross_salary1 field changedInput schema / properties / province / enumPrevious value: -[
- "ON",
- "AB",
- "BC",
- "MB",
- "NS",
- "QC"
-]New value: +[
+ "ON",
+ "AB",
+ "BC",
+ "MB",
+ "NB",
+ "NL",
+ "NT",
+ "NS",
+ "NU",
+ "PE",
+ "QC",
+ "SK",
+ "YT"
+]employee_take_homeemployer_total_costnet_to_gross_salaryVerified Canadian self-employed tax math: SE tax, CPP, GST/HST, instalments, CRA deadlines. Free.
Net pay to the cent, every deduction and the employer's cost for Germany and the UK, computed with…
Live US paycheck and payroll-tax math for 2026, all 50 states and DC, powered by tools-berry.com.
Canada Payroll Calculator: the site's own MCP server — calculator, enquiry (enquiry = a human...
Add one secure layer between your agents and this server.
