Exotic and classic car loan payments with balloons, equity by year, depreciation and lender terms.
Scored across 4 tools
Each tool has a clearly distinct role: single-scenario loan calculation, multi-scenario term comparison, depreciation lookup, and lender lookup. The only potentially adjacent pair, calculate_exotic_car_loan and compare_exotic_car_loan_terms, is clearly separated by single-case versus side-by-side comparison descriptions.
All four names use snake_case with a leading action verb and a domain-specific noun phrase. The calculate/compare/get verb choices are predictable and distinguish the operation type cleanly.
Four tools are well-scoped for a niche loan calculator: calculate, compare, and two supporting lookup tools. There is no obvious filler, and each tool earns its place in the workflow.
The surface covers the core calculator workflow: single payment calculation, term/balloon comparison, depreciation assumptions, and lender data. Minor gaps exist, such as no explicit standalone APR/rate lookup or lease calculation, but agents can work around these using the lender and comparison tools.
Monthly payment on an exotic, classic or collector car loan from your price, down payment, APR, term (36 to 180 months) and optional balloon, using the exoticcar.loans calculator math. Returns amount financed, balloon, total interest, cash at signing, and the estimated car value against the loan balance year by year, with the months (if any) when you would owe more than the car is worth.
| Name | Required | Description | Default |
|---|---|---|---|
| apr | Yes | APR in percent from the borrower's own quote, e.g. 8.5. This server has no rate of its own. | |
| down | No | Down payment in dollars. Default 0. | |
| model | No | Depreciation preset from https://exoticcar.loans/depreciation/ (annualized published figure). Default "all-vehicles" (iSeeCars all-vehicle benchmark). Ignored when value_change_pct is given. | |
| price | Yes | Purchase price in US dollars, e.g. 250000. | |
| months | Yes | Term in months, 36 to 180 (the site offers 36, 48, 60, 72, 84, 96, 120, 144, 180). | |
| balloon_pct | No | Balloon due with the last payment, as a percent of the price, 0 to 60. Default 0. | |
| finance_tax | No | Roll the sales tax into the loan (true, default) or pay it at signing (false). | |
| sales_tax_pct | No | Sales tax rate in percent. Default 0. | |
| value_change_pct | No | Your own expected change in the car's value per year, percent; negative = losing value (e.g. -5). Overrides model. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description earns credit by disclosing the actual return payload – amount financed, balloon, total interest, cash at signing, and year-by-year equity with negative-equity months – which is meaningful since there is no output schema.
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, zero filler; the calculator inputs come first and the return contents second. Dense but every clause carries information.
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 responsibly explains return values and even the negative-equity diagnostic. It doesn't touch the model/value_change_pct depreciation-override behavior or sales-tax financing, but the schema documents those, so the gap is minor.
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 all nine parameters are already documented with ranges, defaults, and enum values. The description restates the term range (36-180) and names key inputs but adds no syntax or semantics beyond the schema, so 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+resource ('Monthly payment on an exotic, classic or collector car loan') and enumerates the inputs (price, down payment, APR, term, balloon) plus a distinctive output (equity/negative-equity months). It is clearly distinct from siblings like compare_exotic_car_loan_terms and get_car_depreciation.
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 strongly implied by 'from your price, down payment, APR...' – it's a single-scenario payment calculator versus the compare tool. However, it never explicitly says when to use this instead of compare_exotic_car_loan_terms or how it relates to get_car_depreciation, leaving the routing inference to the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Side-by-side payment, total interest, balloon and underwater stretch for 2 to 6 term and balloon combinations on the same car, price, down payment and APR (for example 120 vs 180 months, or 0% vs 30% balloon), using the exoticcar.loans calculator math.
| Name | Required | Description | Default |
|---|---|---|---|
| apr | Yes | APR in percent from the borrower's own quote, e.g. 8.5. This server has no rate of its own. | |
| down | No | Down payment in dollars. Default 0. | |
| model | No | Depreciation preset from https://exoticcar.loans/depreciation/ (annualized published figure). Default "all-vehicles" (iSeeCars all-vehicle benchmark). Ignored when value_change_pct is given. | |
| price | Yes | Purchase price in US dollars, e.g. 250000. | |
| options | Yes | Term and balloon combinations, e.g. [{"months":120},{"months":180},{"months":120,"balloon_pct":30}]. | |
| finance_tax | No | Roll the sales tax into the loan (true, default) or pay it at signing (false). | |
| sales_tax_pct | No | Sales tax rate in percent. Default 0. | |
| value_change_pct | No | Your own expected change in the car's value per year, percent; negative = losing value (e.g. -5). Overrides model. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered. The description adds real value beyond that by naming the computed outputs (payment, total interest, balloon, underwater stretch) even though no output schema exists, and by anchoring the results to exoticcar.loans calculator math. It doesn't mention failure modes for invalid option combos, so it isn't a 5.
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?
One sentence, front-loaded with the comparison verb and the four returned metrics, with zero filler. It is a long, clause-heavy sentence that takes a second pass to parse fully, which keeps it from a 5.
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 an 8-parameter tool with full schema coverage, rich annotations and no output schema, the description supplies the missing piece — what the comparison actually returns — plus the domain anchor for the math. Nothing an agent needs to select or invoke it correctly is absent.
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 baseline is 3. The description earns above that by making explicit that price, down payment and APR are held constant across all options and only term/balloon vary — a semantic constraint on how the options array is interpreted that the schema alone states only indirectly.
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?
Names a specific verb (compare) and resource (payment, total interest, balloon, underwater stretch) with explicit scope: 2 to 6 term and balloon combinations on the same car. The examples ("120 vs 180 months, or 0% vs 30% balloon") make it unmistakable against the sibling calculate_exotic_car_loan, which handles a single scenario.
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 gives concrete situations that call for this tool (comparing two terms, or 0% vs 30% balloon), which is strong positive guidance. It stops short of stating when not to use it or naming calculate_exotic_car_loan as the alternative for a single quote, so the routing is inferable rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Published five-year depreciation figures for exotic and luxury models (iSeeCars 2026 study and iSeeCars modeled estimates) annualized the way the calculator uses them, plus Hagerty Price Guide quarterly collector-value changes, each with source, period and date. Search by make or model, or omit query for every row.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Make or model to search for, e.g. "Porsche", "911", "Urus". Omit for all rows. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, closed-world behavior, and the description adds useful context about sources, periods, dates, annualization, and that omitting the query returns every row. It stops short of describing pagination or result-size limits.
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 and sources are front-loaded, and the second sentence gives the query behavior. It is dense but efficient, with no clearly wasted sentences.
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 lookup with one optional parameter and no output schema, the description is complete enough: it identifies the data sources, the period basis, and the row-level metadata the agent will receive.
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 single query parameter is already documented in the schema. The description reinforces make/model search and full-table fallback but adds no new syntax or filtering details 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 names a specific resource (published five-year depreciation figures for exotic and luxury models) and sources (iSeeCars, Hagerty), which clearly separates it from the loan-calculation siblings. An agent can tell this is a data lookup, not a calculator.
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?
It explains how to use the tool: search by make or model, or omit query for all rows. That gives clear operating context, though it does not explicitly state when to prefer this over the loan-related siblings or any exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
What collector-car lenders, lease companies, auction-house lenders and manufacturer captives publish about rates, loan amounts, terms, down payment and eligible cars (dealer, private party, auction, LLC titling), with a link to each lender's own page and the date read. Filter by type or search by name.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Lender name to search for, e.g. "Woodside". | |
| type | No | Kind of lender. Default all. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds valuable context beyond annotations by detailing the returned content (rates, terms, eligible cars, lender page links, date read). It does not discuss pagination or rate limits, but for a simple read-only lookup this is largely sufficient.
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 dense sentence that front-loads the data content and then mentions filtering. It is efficiently sized with no redundant text, though the structure could be slightly more scannable by breaking the content list from the filter instructions.
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 a simple lookup tool with two optional parameters, full schema coverage, and no output schema, the description is nearly complete. It explains what data is returned and how to filter, but omits the default behavior when no filter is applied (presumably returning all lenders).
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 both parameters are fully documented in the schema. The description's phrase 'Filter by type or search by name' merely reiterates parameter function without adding format details or edge-case semantics. Baseline 3 is appropriate when the schema carries the parameter documentation.
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 resource: published terms from specialty car lenders, with specific data fields (rates, loan amounts, terms, down payment, eligible cars). It distinguishes itself from sibling calculation tools by focusing on lender-published information. However, it does not explicitly name or contrast with siblings like calculate_exotic_car_loan.
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 by stating 'Filter by type or search by name,' but gives no explicit guidance on when to choose this tool over alternatives. There are no when-not conditions or named alternatives, leaving the agent to infer that this is for lookup rather than calculation or comparison.
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_exotic_car_loancompare_exotic_car_loan_termsget_car_depreciationget_specialty_car_lendersBoat and yacht loan payments with balloon, tax and insurance; state boat tax; lender terms.
Row-by-row loan amortization schedules: monthly or daily accrual, extra principal, PMI, biweekly.
Exotic car rentals from independent US companies: fleets, published daily rates, rental terms.
Add one secure layer between your agents and this server.
