Student loan RAP payment calculator, 2026 federal loan limits, SAVE/PAYE/ICR end dates (OBBBA).
Scored across 4 tools
Each tool has a clearly distinct purpose: one calculates a RAP payment, one compares repayment plans, one returns loan limits, and one lists transition dates. Although calculate_rap_payment and compare_rap_vs_standard both involve RAP payments, their descriptions make the boundary clear.
All names use snake_case and follow a verb-led pattern: calculate_, compare_, get_. The compare_rap_vs_standard name includes a comparison phrase, but it remains readable and consistent with the set.
Four tools is well-scoped for a focused calculator server. Each tool covers a distinct function, and there are no redundant or filler tools.
The surface covers payment calculation, plan comparison, borrowing limits, and transition dates, which are the core needs for a RAP calculator. Minor gaps exist, such as direct IBR/PAYE comparison or interest-rate lookup, but agents can still handle the main workflows.
Calculates the federal student loan Repayment Assistance Plan (RAP) payment created by the One Big Beautiful Bill Act (P.L. 119-21, HEA sec. 455(q)), open since July 1, 2026. Base payment is 1% to 10% of the WHOLE AGI by $10,000 band ($120 a year flat at $10,000 or less, 10% above $100,000), divided by 12, minus $50 per dependent, never below $10. With balance and rate it also shows the first month: interest paid first, unpaid interest waived (interest subsidy), the up-to-$50 principal match, and a constant-income projection to payoff or cancellation after 360 qualifying payments. Copied from the statute text, not model memory.
| Name | Required | Description | Default |
|---|---|---|---|
| agi | Yes | Adjusted gross income in dollars from the most recent tax return (borrower plus spouse, unless married filing separately). | |
| rate | No | Weighted annual interest rate in percent, for example 6.53. Required with balance. | |
| balance | No | Total RAP-eligible Direct Loan balance in dollars (optional). | |
| dependents | No | Number of IRC sec. 152 dependents claimed. Default 0. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the read-only, idempotent, closed-world safety profile, and the description adds substantial context beyond them: the exact statutory basis, the payment formula, what the optional balance/rate path computes (interest subsidy, $50 principal match, 360-payment projection to payoff or cancellation), and the assumption of constant income. The provenance note (copied from statute text, not model memory) is a meaningful trust signal for 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?
Purpose and statutory grounding are front-loaded, followed by formula then optional-output behavior, so the ordering is sensible. It is dense and formula-heavy in a single block, but nearly every clause conveys computational or trust-relevant information rather than filler.
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?
With no output schema, the description takes on the job of explaining returns, and it does so reasonably: base payment, first-month breakdown, and the payoff/cancellation projection. It does not describe the response shape or units for the projection (e.g., month count vs. total paid), which is a minor remaining gap for a four-parameter calculator.
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%, so the schema carries the baseline, but the description still adds meaning: it explains that dependents subtract $50 each from the monthly figure, that rate is only meaningful together with balance, and that AGI is banded in $10,000 increments with a $120 floor and 10% top rate. That gives the agent a mental model of how each input moves the result.
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 (calculates the RAP monthly payment) and anchors it with the governing statute and effective date. It is clearly distinguishable from siblings like compare_rap_vs_standard and get_plan_transition_dates, which do comparison and date lookup rather than a single-payment computation.
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?
Usage is implied by the formula and by the note that supplying balance and rate additionally yields a first-month and payoff projection, so an agent can infer when the optional params matter. However, it never says when to prefer this over compare_rap_vs_standard or get_plan_transition_dates, and gives no exclusions or preconditions beyond the effective date.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compares the new Repayment Assistance Plan with the Tiered Standard plan (P.L. 119-21: 10 years under $25,000, 15 under $50,000, 20 under $100,000, 25 at $100,000 or more) and, for borrowers with no loan made on or after July 1, 2026, the 10-year Standard plan. Returns monthly payment, months, total paid, interest waived, principal match and the amount cancelled after 360 RAP payments, assuming constant income and on-time payments. Says which plans count for PSLF (RAP yes, Tiered Standard no).
| Name | Required | Description | Default |
|---|---|---|---|
| agi | Yes | Adjusted gross income in dollars from the most recent tax return (borrower plus spouse, unless married filing separately). | |
| rate | Yes | Weighted annual interest rate in percent. | |
| balance | Yes | Total Direct Loan principal in dollars. | |
| dependents | No | Number of IRC sec. 152 dependents claimed. Default 0. | |
| has_loan_on_or_after_2026_07_01 | No | True if any Direct Loan (including a consolidation loan) was made on or after July 1, 2026. Then the old 10-year Standard plan is not available. Default false. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this as a safe read-only, idempotent operation, but the description adds substantial behavioral context: it lists the returned metrics, discloses the assumption of constant income and on-time payments, and notes which plans count for PSLF. Those are meaningful execution details beyond the structured 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 front-loaded with the comparison and remains compact for a five-parameter financial tool. The long parenthetical listing the Tiered Standard income thresholds is informative but dense and could be structured more cleanly.
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, lack of an output schema, and safe read-only annotations, the description is complete enough to call correctly. It names the compared plans, conditions, returned values, key assumptions, and PSLF treatment.
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 schema already documents each parameter thoroughly. The description reinforces the conditional role of the loan-date parameter and the constant-income assumption for AGI, but it does not add syntax or interpretation beyond what the schema 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 uses a specific verb ('Compares') and names the exact plans being compared: RAP, Tiered Standard, and conditionally the 10-year Standard plan. This is far more specific than the sibling calculate_rap_payment tool and makes the tool's scope immediately clear.
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 establishes the comparison context and states the condition under which the 10-year Standard plan is included. It does not explicitly direct the agent away from calculate_rap_payment or explain when a single-plan calculation would be preferable, so it stops short of full alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns federal Direct Loan borrowing limits in force on a date. From July 1, 2026 (P.L. 119-21 sec. 81001): Grad PLUS ends for new borrowers; graduate unsubsidized $20,500 a year / $100,000 aggregate; professional $50,000 a year / $200,000 aggregate; Parent PLUS $20,000 a year and $65,000 total per dependent student across all parents; $257,500 lifetime cap; less-than-full-time proration; the interim exception for students enrolled with a loan on June 30, 2026. Undergraduate limits ($5,500-$7,500 dependent, $9,500-$12,500 independent) from the FSA Handbook.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Date the period of instruction begins, YYYY-MM-DD. Default today (2026-11-02). | |
| borrower_type | No | dependent_undergraduate, independent_undergraduate, graduate, professional, parent_plus or all (default). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds real domain behavior: results change at the July 1, 2026 statutory boundary, proration applies to less-than-full-time enrollment, and an interim exception exists for borrowers enrolled with a loan on June 30, 2026. It stops short of describing the response structure or what happens for dates far outside the stated regimes.
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 purpose sentence is front-loaded and the statutory/date specifics follow in one dense block. Density is justified by the reference nature of the data, though the trailing undergraduate-limits sentence is closer to output preview than invocation guidance.
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?
Two optional parameters, no output schema, and the description supplies all the substantive framing an agent needs: what is returned (annual and aggregate caps per borrower type), the effective-date regimes, proration, and the interim exception. There is no output schema, yet the enumerated amounts effectively preview the return content.
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%, so baseline is 3; the description goes beyond it by explaining why 'date' matters (the pre/post July 1, 2026 regime split) and by giving substance to each borrower_type value (dependent vs independent undergraduate ranges, graduate, professional, Parent PLUS per dependent student). It does not clarify the 'all' enum value or the today-default behavior beyond what the schema says.
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?
Opens with a precise verb+resource+scope: 'Returns federal Direct Loan borrowing limits in force on a date.' The resource (loan limits) is unmistakably distinct from the repayment-plan siblings (transition dates, RAP payment, RAP vs standard), so an agent can route without opening the schema.
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?
Usage is implied by the date-scoped framing ('in force on a date'), which signals this is a point-in-time lookup, but the description never states when to prefer it or what to do instead when a question is about repayment rather than limits. No explicit when-not or alternative routing is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Lists the dated steps of the federal student loan repayment overhaul: SAVE ended by court order (March 2026) with 90-day servicer notices from July 1, 2026 plus a final 30-day notice; RAP and the Tiered Standard plan from July 1, 2026; deferment and forbearance limits on loans from July 1, 2027; PAYE and ICR end and remaining borrowers move to RAP or IBR on July 1, 2028; the Parent PLUS consolidation deadline of June 30, 2028. Marks each as past or upcoming against a date and gives the current status of every plan.
| Name | Required | Description | Default |
|---|---|---|---|
| on_date | No | Reference date YYYY-MM-DD for past/upcoming. Default 2026-11-02. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that by disclosing what the response contains — each step marked past or upcoming against a supplied date, plus a current status per plan — which tells an agent how the data will be shaped.
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?
Purpose is front-loaded in the opening clause, but the sentence then packs six enumerations of dates and deadlines into a single semicolon-chained run-on. That detail is largely payload an agent will receive upon calling, so it costs readability without changing the decision to invoke.
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 read-only, single-optional-parameter tool with no output schema, the description supplies what an agent needs: the domain, the content returned, and the past/upcoming semantics. Only explicit invocation guidance is missing, which is minor given the narrow scope.
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 the schema already defines on_date with format and default. The description only echoes this with 'against a date' and adds no syntax, timezone, or edge-case guidance beyond the structured field, so the baseline 3 applies.
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 — 'Lists the dated steps of the federal student loan repayment overhaul' — and the enumerated content makes the scope unmistakable. None of the siblings (payment calculators, loan limits) retrieve timeline data, so an agent can route correctly without opening a schema.
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?
Usage is only implied: the enumeration of plans and dates suggests 'call this when the user asks about a plan timeline or deadline,' but there is no explicit when-to-use, no when-not-to-use, and no mention of the sibling tools as alternatives. An agent must infer the trigger condition.
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.
calculate_rap_paymentcompare_rap_vs_standardget_federal_loan_limitsget_plan_transition_datesFederal student loan repayment estimates: RAP, IBR, Standard, Tiered Standard, PSLF, refinance.
For borrowers: payments on every federal plan, RAP to PSLF. Free login, 5 questions, no credit card
US federal 2026 tax brackets, standard deductions, payroll and retirement limits, sourced.
2025-2028 car loan interest deduction, SALT cap, child tax credit and 2026 tax brackets (IRS).
Add one secure layer between your agents and this server.
