Skip to main content
Glama

evaluate_purchase

Read-only

Weighs a purchase, loan, or savings goal against a family's real finances—savings, cash flow, debts, emergency fund, goals, and stress-test risk—to show affordability and up to three alternatives.

Instructions

Weighs a purchase against the family's real numbers: what it does to the savings, what is left for living, the loan payment share, the emergency fund and the goals, the stress test, the risk and up to three alternatives. Required by kind: buy_now (own money) — amount, currency; optional goalId when the money was put aside for that goal. credit — amount, currency, termMonths, ratePct, downPayment (in the same currency, below the amount; 0 for none) and loanType. save_up — amount, currency, targetMonth (YYYY-MM, after this month); its goals entry proposed carries requiredMonthly, firstShare and, when nearer goals take savings ahead of it, takenAhead, as in evaluate_goal. A missing required field answers 400 missing_param naming it: ask the family for it, never guess. Every figure is computed by the server in the family currency. Follow answerRules in your answer.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>",
      "amount": "<amount>",
      "currency": "<currency>"
    },
    "name": "evaluate_purchase"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
amountYesThe price, in `currency`
goalIdNobuy_now only: the id of the goal the money was put aside for (from get_family_overview)
ratePctNocredit: the yearly interest rate, %
currencyYesISO 4217 code of the amount, three capital letters, e.g. USD
loanTypeNocredit: the kind of loan
termMonthsNocredit: the term in months
downPaymentNocredit: paid at once, in `currency`, below the amount
targetMonthNosave_up: the month the money is needed, YYYY-MM

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, and the description reinforces it by noting every figure is computed server-side in family currency, so nothing is persisted. It adds the useful failure behavior — a 400 missing_param naming the field — and the 'never guess, ask the family' rule, but says nothing about latency, currency conversion assumptions, or how the alternatives are generated.

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

Conciseness3/5

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

The opening clause is well front-loaded and the per-kind requirements are logically ordered, but the whole thing is one dense run-on paragraph mixing purpose, parameters, error behavior and output description. It would read much better split into purpose / required-by-kind / output sections.

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

Completeness4/5

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

With no output schema, the description does the work of describing the return surface (the enumerated figures plus up to three alternatives) and flags the answerRules the agent must follow. Combined with the documented 400 behavior and per-kind requirements, an agent has enough to call it correctly; only the exact response shape remains unspecified.

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 already 89%, yet the description adds real cross-field meaning: downPayment must be in the same currency and below amount (0 for none), targetMonth must be after the current month, goalId is buy_now-only, and the proposed goal entry carries requiredMonthly/firstShare/takenAhead. That is genuine semantic value -- conditional requirements and relational constraints -- beyond the per-field schema text.

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

Purpose4/5

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

Opens with a specific verb and resource: weighs a purchase against the family's numbers, then enumerates exactly which figures it returns (savings impact, living budget, loan share, emergency fund, goals, stress test, risk, alternatives). It references evaluate_goal for the save_up shape but never states plainly how it differs from that sibling or from preview_loan, so differentiation is hinted rather than made explicit.

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 three kinds (buy_now, credit, save_up) imply which situation maps to which call, and the definition says to ask the family for a missing required field rather than guess. However there is no explicit when-to-use versus preview_loan, preview_proposal, evaluate_goal, or commit_loan — the agent must infer that this is the pre-commit analysis step.

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