Deterministic Canadian CCPC rate stack: small business deduction and grinds, Part IV, RDTOH.
Scored across 4 tools
Each tool serves a distinct purpose: explain (diagnostic), group (associated companies), resolve (single computation), rules (statutory parameters). No overlap in functionality; an agent can easily select the correct tool based on the task.
All tools share the 'ccpcrate_' prefix and use a consistent verb-like action: explain, group, resolve. 'rules' is a noun rather than a verb, which is a minor deviation but still clear and predictable within the set.
Four tools cover the core needs of the domain: compute, explain, group, and rules. This is a well-scoped count that avoids redundancy and keeps the surface manageable.
The tool set provides a complete lifecycle: individual computation (resolve), group handling (group), diagnostic insight (explain), and access to underlying rules (rules). No obvious dead ends; all critical operations are covered.
Free diagnostic pass over the same input as ccpcrate_resolve: which layers run, the defaults the engine would apply, every warning with its meaning (grind binding, provincial asymmetries, missing inputs), the rule rows in force for the year with sources and verification status, the open verifications, and what the paid computation would return. Contains no computed amounts — the numbers are in ccpcrate_resolve.
| Name | Required | Description | Default |
|---|---|---|---|
| qc | No | Québec inputs (CO-771) | |
| taxYear | Yes | ||
| province | Yes | Province of the permanent establishment (two-letter code) | |
| cdaOpening | No | Capital dividend account opening balance (returns cda_closing) | |
| rdtohOpening | No | Opening ERDTOH / NERDTOH in T2 terms. Omitted = 0 with a warning when it matters | |
| taxableIncome | No | Part I taxable income (T2 line 360). Omit for a holdco and supply the income lines instead; the engine derives it | |
| netIncomeForTax | No | Holdco: net income for tax purposes (Sch 1 result) — overrides the derivation | |
| propertyExpenses | No | Holdco: deductible property expenses of the year (total) | |
| groupAaiiPriorYear | No | T2 line 417: Σ Sch 7 line 745 of the associated group for taxation years ending in the preceding calendar year. REQUIRED whenever a business limit is claimed | |
| netIncomeAccounting | No | Holdco: net income per financial statements | |
| otherPropertyIncome | No | Holdco: property income other than dividends and capital-gains dividends | |
| taxableCapitalGains | No | Sch 6: taxable capital gains (the included half) | |
| activeBusinessIncome | No | T2 line 400: income from an active business carried on in Canada | |
| lossesByYearOfOrigin | No | Sch 4 Part 6: opening balances by year of origin, e.g. {"2011": 263564} | |
| provincialProportion | No | Share of taxable income allocated to the province (Reg. 402). Default 1 | |
| capitalGainsDividends | No | Capital-gains dividends received (full amount; half to CDA) | |
| dividendsPaidEligible | No | Eligible dividends paid (designated) in the year | |
| allowableCapitalLosses | No | Sch 6: allowable capital losses of the year | |
| businessLimitAllocated | No | Business limit allocated to this corporation (Sch 23 line 410 if associated, else the statutory limit). 0 = allocation zero | |
| foreignInvestmentIncome | No | T2 line 445: foreign investment income | |
| nonCapitalLossesOpening | No | Sch 4: non-capital loss pool at the start of the year | |
| dividendsPaidNonEligible | No | Non-eligible taxable dividends paid in the year | |
| foreignBusinessTaxCredit | No | T2 line 636: foreign business income tax credit | |
| aggregateInvestmentIncome | No | T2 line 440: aggregate investment income (s.129(4)) | |
| dividendsReceivedConnected | No | Dividends from connected corporations (s.186(4)) — Part IV only through the payer's refund | |
| foreignNonBusinessTaxCredit | No | T2 line 632: foreign non-business income tax credit | |
| taxableCapitalGroupPriorYear | No | T2 line 415: taxable capital employed in Canada of the group, prior year. Omit when under 10 M | |
| dividendsPaidOfWhichConnected | No | How much OF the dividends paid above went to connected corporations — a portion of dividendsPaidEligible + dividendsPaidNonEligible, never an amount on top of them. Raises the cascade warning on the payer side. In a ccpcrate_group call the recipients' own dividendsReceivedConnected amounts govern the 186(1)(b) share; this field is then cross-checked against them | |
| dividendsReceivedPortfolioEligible | No | Eligible taxable dividends from non-connected payers (Part IV → ERDTOH) | |
| nonCapitalLossesClaimedAgainstPartI | No | Non-capital losses claimed against Part I income | |
| nonCapitalLossesClaimedAgainstPartIV | No | Non-capital / farm losses claimed against Part IV (s.186(1)(c),(d)) — the loss amount | |
| dividendsReceivedPortfolioNonEligible | No | Non-eligible taxable dividends from non-connected payers (Part IV → NERDTOH) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states 'Contains no computed amounts', directly reinforcing the readOnlyHint and idempotentHint annotations. It also explains the non-computational nature of the output. No side effects are implied, and no contradiction exists with the annotations.
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 succinct and well-structured, fitting a single dense sentence. It front-loads the core purpose and uses a colon to efficiently list output components without unnecessary wording.
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 there is no output schema, the description lists the main result categories thoroughly enough for an agent to know what to expect. It does not mention potential error cases or detailed output formats, but for a diagnostic tool the described output set is reasonably complete.
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?
The input schema has very high coverage (97%) with detailed field descriptions and nested object explanations, so the description adds little parameter-level semantics. It appropriately points out that the input is identical to ccpcrate_resolve, which is useful, but the schema already carries the parameter meaning.
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 identifies the tool as a diagnostic pass over the same input as ccpcrate_resolve, and enumerates the exact outputs: layers run, defaults, warnings, rule rows, verifications, and the paid computation result. It is distinct from the sibling tools, especially ccpcrate_resolve.
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 explicitly frames the tool as free and diagnostic, with the actual numbers deferred to ccpcrate_resolve, giving agents a strong hint to use this tool for explanation rather than final amounts. It could be more explicit about when to prefer it over ccpcrate_rules or ccpcrate_group, but the contrast with ccpcrate_resolve is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compute a whole associated group (s.256) in one call: federal line 417 as the sum of the members' prior-year adjusted investment income, the Schedule 23 allocation of the business limit, and every member's return in payer-before-recipient order so that a connected dividend's Part IV under s.186(1)(b) is filled in from the payer's own refund instead of being asked for. Returns each member's lines plus what the grind costs the group and which member causes it — the case a single-corporation computation cannot show. 0.25 USDC covers the group and its first 2 computed members, then 0.05 per additional member, never more than 1. Members that only contribute line 417 are free.
| Name | Required | Description | Default |
|---|---|---|---|
| members | Yes | The associated corporations (s.256). A member with no input still counts toward line 417. Order does not matter — the engine computes payers before recipients | |
| taxYear | No | The group's taxation year, used to read the statutory business limit when no member computes | |
| groupAaiiPriorYear | No | Federal line 417 for the group, when the per-member figures are not available. A member's own input.groupAaiiPriorYear still wins |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context: payer-before-recipient computation order, how connected-dividend Part IV is filled in from the payer's refund, the return summary, and a concrete pricing model with a cap and free members. Nothing contradicts the annotations.
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?
Three dense sentences, each earning its place: purpose and computation behavior, return contents and differentiator, and pricing model. The main verb and resource are front-loaded, and there is no filler or redundant restatement of the schema.
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 complex multi-member tax computation with no output schema, the description summarizes the return (member lines, group grind cost, and the member causing it) and the key cascade behavior. The detailed input schema carries the parameter burden; the description provides enough operational context for an agent to invoke the tool correctly, though exact output fields are not enumerated.
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 the baseline is 3, but the description adds meaning beyond the schema by explaining how parameters relate: member prior-year AAI feeds federal line 417, businessLimitAllocated feeds the Schedule 23 allocation, and payerId in dividendsReceivedConnected drives the payer-before-recipient cascade. It also clarifies that members contributing only line 417 are free, which maps to the members array structure.
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 opens with a specific verb and resource: 'Compute a whole associated group (s.256) in one call.' It lists the exact computations involved (line 417, Schedule 23 allocation, Part IV cascade) and contrasts with 'a single-corporation computation,' which helps distinguish it from the sibling resolve tool.
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 clearly signals when to use the tool: when a whole associated group must be computed, especially with connected dividends that require payer-before-recipient ordering. It implies the alternative of a single-corporation computation by saying this is the case a single-corporation computation cannot show, though it does not explicitly name the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compute the federal Part I / Part IV / refundable / RDTOH / dividend-refund lines and the provincial layer for one CCPC and one taxation year. Returns a readable summary plus the structured result: lines (rounded, as printed), unrounded audit values, facts, warnings, layers, balances carried forward, the inputs still missing, engine and rules versions and a request hash. Deductions are negative, taxes positive. A missing required input is an error, not a default. Paid: 0.25 USD per call in USDC over x402 (Base); without a payment the call returns the x402 payment requirements.
| Name | Required | Description | Default |
|---|---|---|---|
| qc | No | Québec inputs (CO-771) | |
| taxYear | Yes | ||
| province | Yes | Province of the permanent establishment (two-letter code) | |
| cdaOpening | No | Capital dividend account opening balance (returns cda_closing) | |
| rdtohOpening | No | Opening ERDTOH / NERDTOH in T2 terms. Omitted = 0 with a warning when it matters | |
| taxableIncome | No | Part I taxable income (T2 line 360). Omit for a holdco and supply the income lines instead; the engine derives it | |
| netIncomeForTax | No | Holdco: net income for tax purposes (Sch 1 result) — overrides the derivation | |
| propertyExpenses | No | Holdco: deductible property expenses of the year (total) | |
| groupAaiiPriorYear | No | T2 line 417: Σ Sch 7 line 745 of the associated group for taxation years ending in the preceding calendar year. REQUIRED whenever a business limit is claimed | |
| netIncomeAccounting | No | Holdco: net income per financial statements | |
| otherPropertyIncome | No | Holdco: property income other than dividends and capital-gains dividends | |
| taxableCapitalGains | No | Sch 6: taxable capital gains (the included half) | |
| activeBusinessIncome | No | T2 line 400: income from an active business carried on in Canada | |
| lossesByYearOfOrigin | No | Sch 4 Part 6: opening balances by year of origin, e.g. {"2011": 263564} | |
| provincialProportion | No | Share of taxable income allocated to the province (Reg. 402). Default 1 | |
| capitalGainsDividends | No | Capital-gains dividends received (full amount; half to CDA) | |
| dividendsPaidEligible | No | Eligible dividends paid (designated) in the year | |
| allowableCapitalLosses | No | Sch 6: allowable capital losses of the year | |
| businessLimitAllocated | No | Business limit allocated to this corporation (Sch 23 line 410 if associated, else the statutory limit). 0 = allocation zero | |
| foreignInvestmentIncome | No | T2 line 445: foreign investment income | |
| nonCapitalLossesOpening | No | Sch 4: non-capital loss pool at the start of the year | |
| dividendsPaidNonEligible | No | Non-eligible taxable dividends paid in the year | |
| foreignBusinessTaxCredit | No | T2 line 636: foreign business income tax credit | |
| aggregateInvestmentIncome | No | T2 line 440: aggregate investment income (s.129(4)) | |
| dividendsReceivedConnected | No | Dividends from connected corporations (s.186(4)) — Part IV only through the payer's refund | |
| foreignNonBusinessTaxCredit | No | T2 line 632: foreign non-business income tax credit | |
| taxableCapitalGroupPriorYear | No | T2 line 415: taxable capital employed in Canada of the group, prior year. Omit when under 10 M | |
| dividendsPaidOfWhichConnected | No | How much OF the dividends paid above went to connected corporations — a portion of dividendsPaidEligible + dividendsPaidNonEligible, never an amount on top of them. Raises the cascade warning on the payer side. In a ccpcrate_group call the recipients' own dividendsReceivedConnected amounts govern the 186(1)(b) share; this field is then cross-checked against them | |
| dividendsReceivedPortfolioEligible | No | Eligible taxable dividends from non-connected payers (Part IV → ERDTOH) | |
| nonCapitalLossesClaimedAgainstPartI | No | Non-capital losses claimed against Part I income | |
| nonCapitalLossesClaimedAgainstPartIV | No | Non-capital / farm losses claimed against Part IV (s.186(1)(c),(d)) — the loss amount | |
| dividendsReceivedPortfolioNonEligible | No | Non-eligible taxable dividends from non-connected payers (Part IV → NERDTOH) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses output structure (readable summary plus structured result with lines, audit values, warnings, etc.), sign conventions (deductions negative, taxes positive), error behavior for missing inputs, and payment behavior. This complements the annotations (readOnlyHint, idempotentHint) without contradiction, giving a full picture of what the tool does and what to expect.
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 dense but front-loaded with the core computation, then efficiently expands into output details, sign conventions, error semantics, and payment. Every sentence adds essential information for a complex tax domain; no filler or redundancy.
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 the tool's complexity and lack of an output schema, the description covers all necessary context: what it computes, what types of outputs are returned, sign conventions, error handling, payment conditions, and scope. This is sufficient for an agent to decide when and how to call it correctly.
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?
Though the schema already covers 97% of parameters, the description adds meaningful context beyond the schema: e.g., 'hours07aCurrentYear required with 07b for the CO-771 layer', 'Omit for a holdco and supply the income lines instead', 'REQUIRED whenever a business limit is claimed', and clarifications like 'never an amount on top of them'. These enrich parameter understanding far beyond the baseline.
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 states a specific action ('Compute'), a specific resource ('federal Part I / Part IV / refundable / RDTOH / dividend-refund lines and the provincial layer'), and a precise scope ('for one CCPC and one taxation year'). This clearly distinguishes it from the group-level sibling ccpcrate_group.
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 explicitly scopes the tool to a single CCPC and single taxation year, implying when to use it versus ccpcrate_group. It also gives concrete usage conditions such as the payment requirement ('Paid: 0.25 USD per call... without a payment the call returns the x402 payment requirements') and clarifies error semantics ('A missing required input is an error, not a default').
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The statutory rates and parameters the engine uses (14 jurisdictions, effective dates, application modes, sources, verification status), filterable by jurisdiction, key and date. Free.
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | Row key (e.g. sbd_rate, business_limit, passive_income_grind); omit for all keys | |
| date | No | Only the rows in force on this date (default: every row, all periods) | |
| jurisdiction | No | Jurisdiction; omit for all |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool returns rules data filtered by jurisdiction, key, and date, which is consistent with the readOnly and idempotent annotations. However, it does not describe the output format, whether multiple rows are returned, or what happens when no match is found. The behavior is predictable for a simple lookup but lacks explicit detail.
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 brief and to the point, using a single sentence to convey the tool's purpose and filtering options. The parenthetical list of data attributes is informative without redundancy. No unnecessary words except perhaps 'Free.', which is minimal.
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?
While the description covers the tool's input and general purpose, it omits any mention of the response structure (e.g., fields returned, list vs. single object). The 'Free.' phrase is unexplained and could confuse. For a simple read-only lookup, this is adequate but not fully complete.
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?
All three parameters (key, date, jurisdiction) have clear descriptions in the schema, including examples, defaults, and enumeration values. The jurisdiction enum perfectly matches the stated 14 jurisdictions. No parameter lacks explanation.
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 identifies the tool as providing statutory rates and parameters, and mentions it is filterable by jurisdiction, key, and date. It does not use an explicit verb like 'retrieve' or 'list', but the meaning is unambiguous. The tool serves as the base query for rules data among its siblings.
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 does not explicitly state when to use this tool versus its siblings (ccpcrate_explain, ccpcrate_group, ccpcrate_resolve). The only hint is that it is filterable, implying it is the direct data accessor. The trailing 'Free.' adds no actionable guidance and may confuse.
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.
ccpcrate_explainccpcrate_groupccpcrate_resolveccpcrate_rulesVerified Canadian self-employed tax math: SE tax, CPP, GST/HST, instalments, CRA deadlines. Free.
Equity comp tax/trade optimizer: ISO/AMT exercise, NSO, RSU, QSBS, concentration, hedging. 50-state.
Deterministic MLP tax engine with IRS citations. 6 tools: basis, §751, estate, projections.
Read-only Canadian GST/HST rates, small-supplier check and CRA allowance rates, with CRA sources.
Add one secure layer between your agents and this server.
