Skip to main content
Glama

evaluate_goal

Read-only

Weigh a new savings goal against your family's real numbers: required monthly contribution, which existing goals move and by how many months, risk, and an adjusted target date.

Instructions

Weighs a new savings goal against the family's real numbers: the monthly contribution it needs, which existing goals move and by how many months, the risk and, when it is out of reach, a later date — or, when no later one within thirty years fits, the nearest earlier date that does. The goals entry proposed is the new goal: requiredMonthly is the contribution it needs a month, an even spread from next month to its date, in the family currency; firstShare is what the plan actually pays into it: the first month it gets money (month, YYYY-MM) and what it gets a month then (perMonth; null — it never gets any) — say when money starts and how much with it, and call requiredMonthly only the even spread, never "requiredMonthly a month from that month"; takenAhead, whenever goals with a nearer or the same deadline take savings ahead of it, is what the goals with a nearer or the same deadline (existing goals first) take a month now (perMonth) and the month the last of them is reached (untilMonth; null — one of them is never reached) — the savings go to the nearest deadline first, and a reached goal's share passes to the next ones. The financial-independence goal's month includes an assumed 8% return a year on what it holds; it stops taking savings that month, so a goal after it is funded from then. A later or earlier date keeps every goal that is on track on track; it may move a goal that is already late, and lists that move. All four fields are required; a missing one answers 400 missing_param naming it. 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": {
      "name": "<name>",
      "amount": "<amount>",
      "currency": "<currency>",
      "targetDate": "<targetDate>"
    },
    "name": "evaluate_goal"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe goal's name
amountYesThe target sum, in `currency`
currencyYesISO 4217 code of the amount, three capital letters, e.g. USD
targetDateYesThe day the money is needed, YYYY-MM-DD, not in the past

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior4/5

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

Beyond readOnlyHint=true, the description discloses substantial behavior: out-of-reach goals get a later date or the nearest fitting earlier date within thirty years, already-late goals may move and those moves are listed, the financial-independence goal assumes an 8% annual return and stops taking savings in its month, and a missing field answers 400 missing_param. This is genuine added context and does not contradict the read-only annotation.

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

Conciseness2/5

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

The definition is a dense block of run-on, comma-spliced sentences covering requiredMonthly, firstShare, and takenAhead in one breath, with meta-instructions like never 'requiredMonthly a month from that month'. The core purpose is front-loaded, but the remainder is hard to parse and poorly structured.

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

Completeness3/5

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

With no output schema, describing return fields is necessary, and the description does cover proposed, requiredMonthly, firstShare, and takenAhead. However, the coverage is tangled and does not cleanly enumerate the return shape, so an agent can call it but may misread what comes back.

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

Parameters3/5

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

Schema description coverage is 100%, so the four inputs (name, amount, currency, targetDate) are already fully documented with patterns and limits. The description spends its words on result fields rather than adding meaning to the inputs, so the baseline of 3 applies.

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?

The opening sentence gives a specific verb and resource: it weighs a new savings goal against the family's real numbers and reports contribution, goal moves, risk, and alternative dates. This is clearly distinct from the name alone, though it never names a sibling such as evaluate_purchase to sharpen the boundary.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. The phrase about the `proposed` goals entry implies a proposal context, but the agent must infer when this tool is appropriate versus preview_proposal or propose_to_family.

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