Skip to main content
Glama

preview_proposal

Read-only

Prepares a family proposal for review without sending it: recomputes the scenario's figures, returns the exact card text the family will see, and asks for explicit confirmation before sending.

Instructions

Prepares a proposal to the family without sending it: the first of two steps. Pass the scenario exactly as you evaluated it (a new goal is kind goal with name and targetDate), the title (at most 80 characters, one line), the short question (at most 300) and your verdict; for the next version of your own proposal that came back (status revising), also its proposalId (leave out the title to keep it). The title, the question, the reason and a new goal's name carry no digits, % or currency signs (a refused one is invalid_param naming it): name it without numbers, not even spelled out — 'a new phone', not 'iPhone 15'; 'the family car', not a model number; the server prints every number on the card. In the verdict, risk is the evaluation's or one step more cautious, never lighter (a refused risk gives params.computed), recommended is one of the evaluation's alternatives or null, and the reason is at most 200 characters. An evaluation whose risk is unknown cannot be proposed: tell the user what data is missing instead. The server weighs the scenario again and answers card.text, the card exactly as the family will get it in Telegram (in the family language); evaluation and baseCurrency, the exact figures behind it, recomputed now: the card rounds amounts to whole units and months to one decimal; a difference within that rounding is not a change. Shares are shown to one decimal too. If the exact figures differ from what you told the user, say so. Also voters (who will be asked to vote; your own vote counts as agree), acceptedAtOnce (true: you are the only voter, so it is accepted at once on sending), a draftId valid for 30 minutes and nextStep. Nothing is sent or stored. Show the user card.text and ask for an explicit yes; then send it with propose_to_family, or revise_proposal for a proposalId. Any change means a new preview.

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": {
      "scenario": "<scenario>",
      "question": "<question>",
      "verdict": "<verdict>"
    },
    "name": "preview_proposal"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoThe proposal's title as the user agreed to it, one line, no digits, % or currency signs: name it without numbers, not even spelled out — 'a new phone', not 'iPhone 15'; 'the family car', not a model number; the server prints every number on the card
verdictYes
questionYesThe short question put to the family, as the user agreed to it, no digits, % or currency signs: name it without numbers, not even spelled out — 'a new phone', not 'iPhone 15'; 'the family car', not a model number; the server prints every number on the card
scenarioYes
proposalIdNoOnly for the next version of your own proposal that came back (status revising): its id, from list_proposals

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint, and the description corroborates it ("Nothing is sent or stored") while adding substantial behavior: draftId lifetime of 30 minutes, refusal payloads (invalid_param, params.computed), the risk-cannot-be-lighter rule, rounding semantics that define when a "change" counts, and the voters/acceptedAtOnce outcome. This is well beyond what the annotation conveys.

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?

Front-loaded with purpose and handoff, and nearly every clause carries operational information (refusals, rounding, draft expiry). It is a dense run-on block, however, and the digit-naming rule is restated from the schema, slightly inflating length over what is strictly needed.

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?

No output schema exists, yet the description enumerates the return payload (card.text, evaluation, baseCurrency, voters, acceptedAtOnce, draftId, nextStep) and explains how to use it. Combined with refusal behavior and rounding caveats, an agent has everything needed to call it and to interpret the result.

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%, and the description adds cross-field rules the schema cannot express: scenario must be passed exactly as evaluated, proposalId applies only to an own proposal in status revising, and omitting title preserves it. Some content duplicates the schema verbatim (the no-digits naming rule appears in both), which keeps it from a 5.

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?

"Prepares a proposal to the family without sending it: the first of two steps" gives a specific verb, resource and scope, and the final sentence names the exact siblings it hands off to (propose_to_family, revise_proposal). An agent can distinguish preview from send/revise without opening another schema.

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

Usage Guidelines5/5

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

States both the flow ("Show the user card.text and ask for an explicit yes; then send it with propose_to_family, or revise_proposal for a proposalId") and the invalidation rule ("Any change means a new preview"). It also gives the precondition for proposalId use (status revising) and the hard stop for unknown risk.

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