Mortgage refinance. Numeratica POST /v1/mortgage/refinance — returns JSON with result_id, engine_version, and a not-advice disclaimer (seed echoed for reproducible Monte Carlo where applicable). See the input schema for the accepted fields.
| Name | Required | Description | Default |
|---|---|---|---|
| new_rate | No | ||
| current_rate | No | ||
| closing_costs | No | ||
| current_balance | No | ||
| new_term_months | No | ||
| roll_in_closing_costs | No | ||
| current_remaining_months | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description discloses return JSON fields and mentions Monte Carlo reproducibility with seed echoing, but does not cover whether the tool is read-only, any side effects, or permissions needed.
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 purpose and endpoint. Concise but could be more structured. No redundant 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 7 parameters and no output schema, the description lacks critical details like what the tool computes (e.g., savings, payment changes) and how parameters relate. The mention of 'seed echoed' suggests an optional parameter not in schema, causing potential confusion.
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 has 0% description coverage and the description does not explain any parameters beyond listing their names in the schema. The agent gets no insight into meaning, constraints, or usage.
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 is for mortgage refinance, specifies the endpoint, and mentions the output format including result_id, engine_version, and disclaimer. It distinguishes itself from other mortgage-related tools like mortgage_affordability.
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?
No guidance on when to use this tool versus alternatives. Does not mention prerequisites, scenarios, or exclusions. The description simply says 'see input schema' without context.
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.
Many tools have nearly identical generic descriptions (e.g., all tax tools say 'Tax ...'), making it hard to distinguish them. Overlapping categories like tax_estimate vs tax_estimated_tax or social_security vs social_security_couple_claim add confusion. With 76 tools, an agent will struggle to pick the correct one.
Most tools follow a consistent snake_case pattern with domain prefixes (e.g., tax_, retirement_, education_). However, a few outliers like 'annuity', 'tvm', 'longevity' break the pattern, and some names are overly long (e.g., 'retirement_withdrawal_sequencing'), but overall the convention is predictable.
76 tools is far excessive for typical MCP servers (ideal is 3-15). Even for a broad financial calculator, this many endpoints raises concerns about maintenance, discoverability, and redundancy. Many tools have identical response structures, suggesting possible consolidation.
The server covers a wide range of financial planning domains: retirement, tax, education, insurance, mortgages, equity compensation, etc. Critical lifecycle operations like calculations for Social Security, Medicare, Roth conversions, and tax estimates are present. Minor gaps exist (e.g., no estate planning tool), but the surface is largely comprehensive.
