Skip to main content
Glama

apibase

by io.github.whiteknightonhorse
OverviewDiscussionsAdmin

SA Municipal — Income & Expenditure

samuni.finance.income_expenditure
Read-onlyIdempotent

Get income and expenditure (Statement of Financial Performance) data for a South African municipality. Returns audited actual (AUDA) annual line items from the mSCOA chart of accounts. Covers revenue sources (rates, grants, service charges) and expenditure categories (employee costs, repairs, capital transfers). Data is Section 71-level aggregation from 2019-20 onwards. Requires demarcation code (e.g. CPT, JHB, ETH, TSH, EKU, BUF). No auth required. Source: SA National Treasury MFMA incexp_v2 cube.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoFinancial year-end to retrieve (e.g. 2022). Omit for all available years. Returns audited actual figures (AUDA) at annual period level.
limitNoMaximum line items to return (1-200, default 50).
demarcation_codeYesMunicipality demarcation code (e.g. CPT=Cape Town, JHB=Johannesburg, ETH=eThekwini, TSH=Tshwane, EKU=Ekurhuleni, BUF=Buffalo City). Required.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent only when the call failed. Includes error code, message, request_id, and any provider-specific extras.
resultNoTool response payload. Shape varies per tool — consult the tool description and inputSchema. May be an object, array, string, or number depending on the upstream provider response.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare read-only and idempotent behavior. The description adds value by specifying the data source (National Treasury MFMA), time range (2019-20 onwards), aggregation level (Section 71), and that no auth is required. It doesn't contradict annotations.

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 description is about 5 sentences, front-loaded with the purpose, and each sentence adds a distinct fact (content, source, range, requirement, auth). No fluff.

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 an output schema present, the description needn't explain return structure. It covers data semantics, time coverage, required input, and source. Minor gaps like pagination behavior are left to the schema, so it's fairly complete.

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 coverage is 100%, so baseline is 3. The description gives example demarcation codes and lists the data categories, but does not explain the year or limit parameters beyond what the schema already says.

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 opens with a specific verb ('Get') and resource ('income and expenditure... data'), and details the content (audited actual line items, revenue/expenditure categories). This clearly distinguishes it from sibling tools like samuni.finance.audit_opinions.

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 usage for retrieving municipal financial performance data and specifies a required parameter (demarcation_code), but it never explicitly compares to alternatives like audit opinions or reference tools, so an agent has to infer when to choose it.

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

All apibase toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources