Skip to main content
Glama
Sign In
drebedengi-mcp

drebedengi-mcp

by hawk911
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Отчёт по категориям / источникам

get_report
Read-only

Generates expense totals by category or income totals by source for a chosen period, with optional monthly, weekly, or daily averaging and currency conversion.

Instructions

Суммы расходов по категориям (group_by=category) или доходов по источникам (group_by=source) за период, с опциональным усреднением по месяцам/неделям/дням и конвертацией в одну валюту. Строки родительских категорий включают дочерние.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoТолько операции с этими тегами
periodNoПериод: today, this_month (по умолчанию), last_month, this_quarter, this_year, last_year, all_time, last_20. Игнорируется, если заданы date_from/date_to.
averageNoУсреднение
date_toNoКонец периода YYYY-MM-DD (включительно)
accountsNoТолько эти счета (id или названия)
currencyNoПересчитать всё в эту валюту (код, например RUB, или id)
group_byNocategory
date_fromNoНачало периода YYYY-MM-DD
categoriesNoТолько эти категории расходов / источники доходов (id или названия)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover the readOnlyHint safety profile, so the description must supply the rest. It does: it discloses that rows for parent categories include their children, calls out optional averaging by month/week/day, and states that currency conversion is applied to everything. Missing are the response shape and pagination, and how totals are computed, but otherwise the description adds useful context.

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?

Two sentences: the first covers what the tool computes and the modifiers, the second covers an important aggregation rule. It is front-loaded with the core purpose, and nothing is repeated or wasted.

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?

No output schema exists and there are 9 parameters, so the description needs to cover the result. It describes categories as 'строки' and explains the parent/child rollup, which partly implies the shape of the return value, but leaves unclear whether totals, counts or nested breakdowns come back. That gap is minor for a read-only report tool.

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?

At 89% schema description coverage, the schema already documents period, dates, averaging, currency and filter parameters, so a baseline of 3 is warranted. The description adds the meaning of group_by in plain language and the parent/child aggregation rule, but does not explain how the period enum interacts with date_from and date_to in more detail than the schema does.

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?

The description names a specific output (expense sums per category / income sums per source), the axis controlled by group_by, the period, and the optional averaging and currency conversion. This clearly distinguishes it from siblings such as get_balance (balances) and get_transactions (raw records).

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 words 'отчёт по категориям или источникам' imply how the tool should be used for aggregation, and group_by is explained as the switch between the two modes. However, the description never states when to prefer this tool over get_transactions or get_balance, and never names the conditions that would exclude it.

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