homes-loan-calculator

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

No annotations exist, so the description carries the full burden. It does disclose the return shape (both EMIs, net saving, break-even months) and that the fee defaults to zero, but it says nothing about the underlying assumption set — whether tenure is held constant, whether the fee is financed or paid upfront, or that the tool is a pure calculation with no side effects.

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 waste: the first front-loads inputs and outputs, the second supplies a compact example that resolves unit and formatting ambiguity. Nothing is repeated or padded.

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 and no annotations, the description steps up by enumerating the three returned values, which is exactly what an agent needs to decide whether to call it. The remaining gap is methodological — the assumptions behind the saving and break-even figures — which matters for a financial comparison but is not stated.

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%, including units (rupees, annual percent) and bounds, so the schema already does the heavy lifting and baseline 3 applies. The description adds only marginal meaning beyond it — a default of 0 for processingFee and a concrete worked example that clarifies expected magnitude and format.

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-plus-resource framing: it names the exact inputs consumed (outstanding balance, months left, current/new rates, fee) and the exact outputs produced (both EMIs, net saving, break-even months). This makes it unmistakably a balance-transfer comparison calculator rather than a plain EMI tool, though it never names a sibling to route against.

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 by the tool's domain: an agent can infer it applies when a borrower is considering refinancing an existing loan. There is no explicit statement of when to prefer it over emi or sensitivity, and no prerequisites (e.g., that a processing fee of 0 is assumed when omitted) are called out.

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 exist, so the description must carry the burden. It does disclose the full output set and gives a concrete example input, which implies a pure calculation with no side effects, but it never states that explicitly, nor does it mention rounding, currency assumptions beyond the schema, or jurisdiction for stamp duty.

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 plus a compact example — the return values are front-loaded and every clause carries information. No 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 one input parameter, no output schema and a calculation-only behavior, the description covers what an agent needs: the input, the example, and the shape of the response. Only the stamp-duty assumptions (rate/jurisdiction) and the read-only nature are left implicit.

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 parameter is already documented as 'Property price in rupees' with an exclusive minimum. The description reinforces this with a sample value of 7500000 but adds no format, unit or range guidance beyond what the schema supplies.

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 (takes a property price) and enumerates exactly what is returned: LTV ratio, maximum loan, minimum down payment, stamp duty and registration. That is far more than the vague tool name 'downPayment' conveys, though it never names a sibling tool to differentiate itself from emi or eligibility.

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 — an agent can infer this is the tool for down-payment/loan sizing given a price. There is no explicit 'use this when' statement and no pointer to emi, eligibility or rentVsBuy as alternatives for related questions.

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 the full burden: it does disclose the core input-output relationship (income, EMIs, rate, tenure → max EMI and loan amount), which is the main behavioral fact. It does not state that this is a pure/read-only computation, nor does it address what happens when both months and years are supplied or how defaults are applied.

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 tight sentences: purpose first, then a compact illustrative example. Every part earns its place, though the example is borderline redundant given 100% schema coverage.

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 exists, and the description does name the two return values, so an agent knows what comes back. For a 6-parameter calculator, the remaining gaps (foir semantics, tenure conflict handling, defaulting behavior) are modest but real.

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, and the description adds value with a concrete example input that grounds units and magnitudes (rupees, percent, years). It still does not explain the foir parameter or the months-vs-years precedence, so it does not fully compensate for that ambiguity.

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 verb (returns), the computation (maximum EMI and home loan amount a borrower qualifies for), and the inputs it consumes. It is clearly distinguishable from siblings like emi or sensitivity by its qualification/eligibility framing, though it never names those siblings explicitly.

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 phrase 'maximum EMI and home loan amount a borrower qualifies for,' so an agent can infer this is the eligibility/affordability calculator rather than a plain EMI tool. However, there is no explicit when-to-use versus emi or sensitivity, and no mention of prerequisites or how it relates to the other siblings.

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 the burden well by disclosing that it supports optional prepayments and rate changes and that it returns EMI, total interest, and a yearly schedule. It omits edge-case behavior (e.g. if both years and months are supplied, rounding/precision) and has no output schema, so a minor gap remains.

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 well-formed sentences: the first front-loads inputs and outputs, the second gives a concrete example. Efficient with little waste; slightly dense but appropriately sized for a 9-parameter tool.

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 9 parameters, nested objects, no annotation coverage, and no output schema, the description supplies the key behavioral shape (inputs, optional features, returns) and an example. It stops short of covering precedence rules and failure modes, but overall it is complete enough to invoke the 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 description coverage is 100%, so the schema already documents every parameter including enums and nested objects, establishing a baseline of 3. The description reinforces this by naming prepayments and rate change and providing a concrete example input, but adds no semantics 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 calculation ('returns the monthly EMI, total interest and year-by-year schedule') on a specific resource domain (Indian home loan), which is clearly distinct from siblings like sensitivity or eligibility. It does not explicitly name or differentiate itself from those siblings, keeping it at 4 rather than 5.

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 the tool's role (compute EMI given loan parameters) but gives no explicit when-to-use/when-not guidance and never mentions alternatives such as sensitivity, which plausibly also computes EMI variants. Usage is inferable but not steered.

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 are provided, so the description carries the full burden. It does disclose the return shape (year-by-year net worth, break-even year), but stays silent on modeling assumptions that materially change results — maintenance, property tax, transaction costs, whether rent grows annually or compounding of investReturn — leaving the agent unable to predict output behavior fully.

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, front-loaded with the core purpose, followed by a worked example. The example JSON is bulky but earns its place given nine required numeric parameters. No filler or marketing language.

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 and no annotations, the description does the necessary work by naming the return values (year-by-year net worth and break-even year). It falls short of fully complete for a financial model by omitting the cost assumptions embedded in the calculation, which an agent may need to set user expectations.

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 adds value by grouping the nine inputs semantically (rent, price, down payment, loan terms, growth assumptions) and by providing a concrete example input with realistic values that shows unit scale and typical magnitudes beyond the schema's unit notes.

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 computation (year-by-year net worth of buying vs renting) plus the key output (break-even year), and enumerates the input domain. This is clearly distinguishable from siblings like emi, downPayment, or sensitivity.

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 example input implies a full buy-vs-rent scenario comparison, but there is no explicit when-to-use guidance, no statement of when a sibling like sensitivity or emi would be the better choice, and no prerequisites. Usage must be inferred from the description and example.

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 the full burden. It discloses the core behavior (per-step recomputation of EMI and total interest) and supplies a concrete input example, but says nothing about what happens when 'deltas' is omitted, whether a default step grid applies, or the shape of the returned comparison.

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, front-loaded with the computation and followed by a compact literal example. Every element earns its place; only the example's redundancy with the schema keeps it off 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?

There is no output schema, and the description only broadly names the return values without indicating structure (per-delta rows, units, sign convention). For a 5-parameter analysis tool it is adequate but leaves the response shape ambiguous.

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%, including ranges and the 'give months or years' hint, so the schema does the heavy lifting. The description's example pins three of the five fields but adds no meaning for 'deltas', the parameter most likely to be misused.

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 computation: takes principal, annual rate and tenure, and returns how EMI and total interest shift as the rate moves in small steps. That distinguishes it in substance from the plain 'emi' sibling, though no sibling is named explicitly.

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 when-to-use is only implied by the word 'sensitivity' and the worked example; there is no statement of when to prefer this over 'emi' or of any preconditions. An agent can infer the scenario but must do the inference itself.

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