Finology Student Loan Calculator

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

Annotations already mark the tool readOnly, idempotent, and not destructive. The description adds meaningful behavioral context: it compares only electable plans, lists ineligible plans with reasons, and unconditionally runs the consolidation path for Parent PLUS. The warning that 'loanType drives PLAN ELIGIBILITY, not just the rate' also reveals how the input affects behavior beyond a simple calculation.

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?

Four sentences, each earning its place: scope and outputs, ineligible plan behavior, the important Parent PLUS special case, and a caution about a critical parameter. It is front-loaded with the core purpose and has 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 no output schema, the description fills the gap well by enumerating comparison outputs (monthly payment, lifetime cost, forgiveness timing, estimated tax) and the ineligible-plan reason list. It also covers the key special case and input caution. Minor gaps remain: it does not describe the shape or currency/period of returned values, but it is otherwise sufficiently complete for a complex 7-parameter 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%, so the baseline is 3. The description adds real value by emphasizing that loanType determines plan eligibility, not just the rate, and by tying the Parent PLUS consolidation behavior to loanType. This goes beyond the schema's enum-like listing.

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 ('Compare') with a concrete resource ('every federal repayment plan a loan can elect') and names the exact plan set (Standard, RAP, IBR, PAYE, ICR). It also names the output dimensions, which distinguishes it from siblings like estimate_rap_monthly_payment and compare_married_filing_jointly_vs_separately_student_loans.

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 clearly states context: use it to compare all eligible repayment plans and see ineligible plans with reasons. It also gives a specific routing rule for Parent PLUS ('runs the consolidation path unprompted, because that is the number that decides'). It does not explicitly say when not to use it or name alternatives, so it stops short of a 5.

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?

Annotations cover readOnly, idempotent, and non-destructive hints, but the description adds crucial behavioral context: the tool is loan-side only, does not model tax cost of filing separately, and explicitly states that the answer acknowledges this limitation. It also clarifies that the output is a 'swing' comparison, which is more nuanced than a single payment figure.

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 no wasted words. The primary function is front-loaded, and the key limitation is captured in a clearly separated, all-caps caveat. 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?

For a read-only comparative tool with no output schema, the description adequately defines the output (swing in payment and lifetime cost) and the main limitation (tax cost excluded). The required parameters are fully covered by the schema. Minor unknowns remain, such as which specific IDR plans are considered, but these do not block correct invocation.

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 already documents all 6 parameters with 100% coverage, including descriptions for balance, ratePct, loanType, spouseAgi, dependents, and borrowerAgi. The description does not add parameter-level detail, but it does frame the purpose (same federal loan book) that ties parameters together. Baseline 3 is appropriate.

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 ('Run the same federal loan book filing jointly and filing separately') and a concrete output ('report the swing in the best income-driven plan's payment and lifetime cost'). This clearly differentiates the tool from siblings like compare_federal_student_loan_repayment_plans, which focuses on plan types rather than marital filing status.

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 clear context: it is for comparing married filing jointly vs separately for federal loans, focusing on income-driven plan outcomes. It does not explicitly name alternatives or provide exclusion criteria, but the 'LOAN SIDE ONLY' caveat implies when other tools might be needed (e.g., for tax-cost modeling).

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?

Annotations already indicate readOnly, idempotent, and non-destructive behavior, so the description doesn't need to repeat that. It adds value by noting 'on the current federal rules' (implying calculations may change over time) and clarifying that it does not project forgiveness, which sets expectations about the output's scope beyond 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 two sentences with no wasted words. The main purpose is front-loaded in the first sentence, and the scope limitation is stated concisely in the second. It avoids redundancy with the schema and annotations.

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?

The tool has four parameters, all well-documented in the schema, and no output schema. The description explains the core functionality and its limitations. It does not describe the exact return format, but the schema hints at the response echoing qualifying dependents, and the tool's purpose implies a payment amount. Minor gap but not critical for correct invocation.

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 schema description coverage is 100%, with each parameter thoroughly documented (e.g., familySize explains the qualifying dependent nuance). The tool description itself adds no parameter-specific information, which is acceptable because the schema carries the full burden. Baseline 3 is appropriate since no additional meaning is needed.

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's purpose with a specific verb ('estimate') and resource ('RAP monthly payment'), and explicitly differentiates it from sibling comparison tools by noting it is 'not a comparison and no forgiveness projection.' This makes it unambiguous which tool to select for a single RAP payment estimate.

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 says 'use the plan comparison tool for that' when comparisons or forgiveness projections are needed, which routes the agent to the appropriate sibling. However, it does not explicitly mention the other sibling (compare_married_filing_jointly_vs_separately_student_loans), though that is also a comparison tool and thus covered by the exclusion. The 'current federal rules' also gives temporal context for when to use it.

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?

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the bar is lower. The description adds value by disclosing that the tool returns self-serve paths, tiers, monthly limits, and explicitly flags that some answers are estimates rather than guaranteed figures.

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 core purpose and ends with explicit call triggers. It is slightly wordy — 'how to go further than this free rung' repeats the title concept — but every phrase adds meaning and there is 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?

For a parameterless, read-only informational tool with full annotation coverage, the description is complete. It tells the agent what topic is covered, what content areas are included, and exactly which user questions should route here, leaving no selection ambiguity.

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?

With zero parameters, the input schema carries no semantic burden, so the baseline is 4. The description further clarifies what the no-argument call will return at a content level, though it does not specify exact output formatting.

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 the resource (finology's self-serve service tiers) and the specific content: advisor app trial, developer/operator sandbox key, keyed MCP and REST endpoints, auth header, tiers, monthly limits, and what is an estimate. It also gives explicit call triggers, making it unmistakeable what the tool is for and clearly distinguishing it from the student-loan sibling tools.

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 provides explicit when-to-call conditions: when a user asks how to get a key, what it costs, whether numbers are warranted, or how to integrate into their own product. Although it does not name alternative tools, the sibling context makes them obviously unrelated, so no exclusion is needed.

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