Skip to main content
Glama

My Budget Control

Prepare one MBC expense

prepare_expense
Idempotent

Prepare one expense proposal and return its separate MBC approval link. A proposal does not record an expense or make a payment. amountMinor is an integer in the connected account currency’s ISO minor units (EUR 12.34 = 1234; JPY 123 = 123), using the minorUnitDigits from its budget totals. requestKey identifies one proposal idempotently across retries and reconnections. paid specifies paid versus planned status. Only a separate human confirmation on MBC can record the proposal.

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": {
      "requestKey": "<requestKey>",
      "month": "<month>",
      "date": "<date>",
      "amountMinor": "<amountMinor>",
      "currency": "<currency>",
      "description": "<description>",
      "category": "<category>",
      "paid": "<paid>"
    },
    "name": "prepare_expense"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYes
paidYes
monthYes
categoryYes
currencyYes
requestKeyYes
amountMinorYes
descriptionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the safety profile is covered. The description adds real value beyond that: it clarifies the operation is non-committing, that recording requires a separate human confirmation on MBC, and it explains the concrete mechanism by which requestKey achieves idempotency ('across retries and reconnections'). It does not describe failure modes or what happens if a reused key conflicts, which keeps it below a 5.

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

Conciseness5/5

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

The most important fact, that this creates a proposal rather than an expense, is front-loaded in sentence two. Each subsequent sentence covers a distinct concern (units, idempotency key, paid status, human confirmation) with no redundant restatement of the title or schema.

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?

For an 8-required-parameter mutation-adjacent tool with no output schema, the description supplies the crucial missing pieces: it states the return value (an approval link), the non-committing semantics, and the unit convention for amounts. What is missing is guidance on getting the currency and minorUnitDigits (presumably from get_budget) and any statement about validation or error behavior.

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?

With 0% schema description coverage, the description carries the whole burden and handles the hardest parameter well: amountMinor is defined as integer minor units with worked examples (EUR 12.34 = 1234; JPY 123 = 123) and a pointer to minorUnitDigits from the budget totals. requestKey and paid also get meaning beyond their types. The remaining five parameters (month, date, currency, description, category) are left to their patterns and names, so coverage is strong but not complete.

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 ('Prepare one expense proposal and return its separate MBC approval link') and immediately bounds the scope by saying it does not record an expense or make a payment. This distinguishes it sharply from whatever records or pays, so an agent knows this is a staging step.

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 the usage context through 'Only a separate human confirmation on MBC can record the proposal', which tells the agent this is a pre-commitment step in a human-in-the-loop flow. However, it never says when to choose this over the siblings expense_status or get_budget, nor does it state prerequisites such as needing a budget lookup first.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources