compare_loansCompares two to five loan scenarios and reports which is cheapest by monthly payment and which by lifetime cost, separately, because they frequently are not the same loan. Use for 15-year versus 30-year, FHA versus conventional, competing lender quotes, or with and without discount points.
| Name | Required | Description | Default |
|---|---|---|---|
| scenarios | Yes | Two to five loan scenarios to compare side by side. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the tool is clearly safe. The description adds valuable behavioral context: it reports the cheapest by monthly payment and by lifetime cost separately because they often differ, which is a non-obvious output behavior.
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: the first states the core function and output, the second lists use-case examples. It is front-loaded with the verb 'compares' and contains no redundant or filler content.
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 a rich input schema and clear annotations, the description explains the tool's purpose, output highlights (two separate cheapest categories), and common use cases. There is no output schema, but the description states what the report contains. It does not detail edge cases or calculation assumptions, but these are largely covered by the schema.
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 parameter 'scenarios' is fully documented in the input schema. The description's mention of 'two to five' scenarios repeats schema constraints (minItems=2, maxItems=5) without adding new semantic meaning. Examples like '15-year versus 30-year' provide mild usage context but do not go 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 clearly states the tool compares two to five loan scenarios and reports the cheapest by monthly payment and lifetime cost separately. This distinguishes it from sibling tools that calculate individual metrics for a single scenario, and concrete examples (15-year vs 30-year, FHA vs conventional) further clarify its purpose.
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 lists when to use it: 15-year versus 30-year, FHA versus conventional, competing lender quotes, and with/without discount points. It implies single-scenario calculations should go to sibling tools like calculate_mortgage, but it does not explicitly name alternatives or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct calculation or information need: affordability, amortization, full mortgage payment, PMI, property tax, refinancing, rent vs buy, loan comparison, closing costs, state rules, and state list. Even overlapping tools like calculate_mortgage and calculate_pmi are clearly separated by depth and purpose.
All tool names follow a consistent verb_noun snake_case pattern, using verbs like calculate, compare, estimate, get, and list. The pattern is uniform and predictable across the entire set.
With 11 tools, the server is well-scoped for a US mortgage calculator domain. Each tool covers a meaningful aspect of mortgage analysis without redundancy or bloat.
The tool surface covers the full lifecycle of mortgage decision-making: affordability, payment estimation, amortization, PMI, property tax, refinancing, rent vs buy, loan comparison, closing costs, and state-specific rules. No significant gaps are apparent for the stated purpose.