Skip to main content
Glama
chrischall

homes-mcp

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Calculate max affordable home price

homes_calculate_affordability
Read-onlyIdempotent

Calculate your maximum affordable home price under the 28/36 DTI rule using income, debts, down payment, and interest rate. Get the binding limit and full PITI breakdown.

Instructions

Solve for the maximum home price you can afford under the standard 28/36 DTI rule. Inputs: monthly income, recurring monthly debts (car loans, student loans, etc.), down payment, interest rate, and optional property-tax rate / insurance / HOA / loan term. Output: max home price, the binding constraint (front-end vs back-end), and the full PITI breakdown at that price. Same math across the realty MCP cohort (@chrischall/realty-core). No network — pure local math.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hoa_monthlyNo
back_end_dtiNoBack-end DTI cap as decimal, default 0.36
down_paymentYes
front_end_dtiNoFront-end DTI cap as decimal, default 0.28
interest_rateYesAnnual %, e.g. 6.5
monthly_debtsNoSum of monthly debt payments (car, student loans, etc.)
monthly_incomeYes
loan_term_yearsNoDefault 30, max 50
insurance_annualNo
property_tax_rateNoAnnual % of home price, default 1.1

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv2.1.7
    • addedInput schema / properties / back_end_dti / description
      Added value: +"Back-end DTI cap as decimal, default 0.36"
    • addedInput schema / properties / back_end_dti / exclusiveMinimum
      Added value: +0
    • removedInput schema / properties / back_end_dti / minimum
      Removed value: -0
    • addedInput schema / properties / front_end_dti / description
      Added value: +"Front-end DTI cap as decimal, default 0.28"
    • addedInput schema / properties / front_end_dti / exclusiveMinimum
      Added value: +0
    • removedInput schema / properties / front_end_dti / minimum
      Removed value: -0
    • addedInput schema / properties / interest_rate / description
      Added value: +"Annual %, e.g. 6.5"
    • addedInput schema / properties / loan_term_years / description
      Added value: +"Default 30, max 50"
    • changedInput schema / properties / loan_term_years / maximum
      Previous value: -9007199254740991New value: +50
    • addedInput schema / properties / monthly_debts / description
      Added value: +"Sum of monthly debt payments (car, student loans, etc.)"
    • addedInput schema / properties / property_tax_rate / description
      Added value: +"Annual % of home price, default 1.1"
  2. Changed1 schema field changedv2.0.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. First observedv1.1.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint=false, and idempotentHint=true; the description reinforces this with 'No network — pure local math,' which explains why it is safe and deterministic. It also discloses the return shape (max price, binding constraint, PITI breakdown), which the absent output schema would otherwise leave opaque. It does not mention auth or error behavior, but for a pure local computation that is minor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences that are front-loaded with the purpose before inputs and outputs. The cohort-consistency sentence ('Same math across the realty MCP cohort') is arguably peripheral, but it earns partial keep by signaling portability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly carries the return burden by naming the three outputs, and it enumerates inputs and the math model. For a deterministic, side-effect-free calculator this covers everything an agent needs to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60% across 10 params. The description enumerates the inputs (monthly income, recurring monthly debts, down payment, interest rate, optional property-tax rate / insurance / HOA / loan term) and the '28/36' framing conveys the meaning of the two DTI-cap params that the schema documents separately. It adds the PITI concept that ties property_tax_rate, insurance_annual, and hoa_monthly together.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Solve for the maximum home price you can afford') and names the governing method (28/36 DTI rule). An agent can distinguish this from homes_calculate_mortgage, which computes payments rather than a max price, without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when the tool applies (you want the maximum affordable price) and names its method, but never explicitly says when to use it over homes_calculate_mortgage or homes_estimate_rent_vs_buy, nor states any exclusion. Usage is inferred rather than routed.

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

Deploy Server

Other Tools