Canada Payroll — employer cost & take-home math (2026)

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

With no annotations provided, the description carries full burden. It transparently discloses assumptions (full-year employee, basic TD1 claims), scope (2026, regular salary), and included deductions. It does not mention side effects or destructive behavior, which are likely irrelevant.

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 a single paragraph with key information front-loaded. It efficiently covers purpose, assumptions, and supported regions without redundancy. A minor improvement could be separating into bullets, but it's effective.

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?

Given 3 parameters, no output schema, and complexity, the description adequately covers inputs and assumptions. It explains what deductions are included and outputs (net pay). Missing explicit output format is acceptable; agent can infer return structure.

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?

Input schema has 100% description coverage, so baseline is 3. The description adds context: pay_frequency default is biweekly and it shows per-period view. This provides moderate added value 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 calculates 2026 take-home pay for a Canadian employee, specifying deductions (CPP/QPP, EI, QPIP, taxes) and outputs (net pay per year/per period). It distinguishes itself from siblings like 'employer_total_cost' and 'net_to_gross_salary' by focusing on employee perspective.

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 implies usage for calculating employee take-home pay under standard assumptions, but does not explicitly mention when to use this tool versus siblings or provide exclusion criteria. Usage is inferred rather than stated.

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

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

With no annotations, the description carries full burden. It explicitly lists what is included (CPP, CPP2, EI, etc.) and excluded (workers' comp, EHT, vacation pay, benefits), ensuring the agent understands the scope and that nothing is silently omitted.

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 two sentences, front-loads the purpose, and packs essential details without redundancy. Every phrase adds value.

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?

Given no output schema, the description explains inputs, supported geography, and what is included/excluded. It lacks explicit output format (e.g., 'returns a number in CAD') but is sufficient for a computation tool with clear purpose.

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% and both parameters are well-described in the schema. The description adds context about the formula and supports the values but does not significantly enhance parameter understanding beyond what the schema already provides.

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 the total cost of a Canadian employee to the employer in 2026, including mandatory contributions and disclosing excluded items. It distinguishes itself from siblings (employee_take_home, net_to_gross_salary) by focusing on employer-side costs.

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 specifies it is for annual planning figures and lists all supported provinces. It does not explicitly state when to use this tool versus siblings, but the purpose (employer cost vs. take-home or conversion) is clear enough to guide selection.

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

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

No annotations provided, so description must disclose behavior. It details outputs: gross salary, employer total cost, per-period remittances with CRA split for Quebec. Mentions it's a 'wedge tool' for nanny/household context. Could add more on return format, but covers core behavior.

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 front-loaded purpose. First sentence captures main action and example. Second sentence adds context (PDOC comparison and supported provinces). Could be slightly tighter (e.g., 'wedge tool' phrase), but every sentence earns its place.

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?

Given no output schema, description explains return values (gross salary, total cost, remittances). Covers provincial support and Quebec split. Doesn't mention error conditions or valid ranges beyond schema's exclusiveMinimum. Still fairly complete for a payroll inversion tool.

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%, but description adds valuable context: target_net_pay is agreed take-home per period in CAD, pay_frequency listed as 'how often', province codes enumerated. The example '$800/week' clarifies target_net_pay. Adds meaning beyond enum labels.

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?

Clearly states it inverts payroll from net to gross, with specific verbs 'invert' and 'get'. Distinguishes from sibling tools (employee_take_home, employer_total_cost) by combining both outputs. Mentions unique value: PDOC only goes gross→net, so this fills a gap.

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 says when to use: when you have agreed take-home pay and need gross salary, total cost, and remittances. Contrasts with PDOC to imply the opposite direction. Lists supported provinces, implicitly telling when not to use (unsupported provinces).

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