Skip to main content
Glama
ariregister-mcp

ariregister-mcp

by aanndryyyy

Get annual report figures

get_annual_report_figures
Read-only

Retrieve annual report figures such as balance sheet, income statement and cash flow for an Estonian company by registry code, optionally filtered by year and report code.

Instructions

Line items of a company's annual report: balance sheet, income statement, cash flow and so on, with this year's and the previous year's values (XML service, needs contract username and password). Without year it lists the available reports (year, report code, name). With year and no report_code it returns every report for that year (one query each); pass report_code (from the list) for just one.

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": {
      "registry_code": "<registry_code>"
    },
    "name": "get_annual_report_figures"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNoReporting year.
languageNoLanguage of classifier texts (statuses, roles, legal forms): 'eng' (default) or 'est'.
report_codeNoReport code from the list, e.g. '01' (balance sheet).
registry_codeYes8-digit Estonian registry code (registrikood), e.g. 14663023. Find it with search_companies.

Output Schema

NameRequiredDescriptionDefault
yearNo
messageNo
reportsNo
availableNo
registry_codeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint and openWorldHint, so the description does not need to establish safety. It still adds real value beyond them: the backend is an XML service requiring contract username and password, and the multi-report mode issues one query per report. However, it says nothing about latency, failure modes, or partial results when one of those queries fails.

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?

Three sentences, front-loaded with what the tool is, then the credential caveat, then the parameter branches in ascending specificity. Dense but every clause carries information; the parenthetical about the XML service is slightly tucked away mid-sentence rather than at the end.

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, return shapes need no explanation, and the description correctly focuses on invocation modes, auth prerequisites, and query cost. Combined with full schema coverage, an agent has what it needs to call this correctly; only the boundary against `list_annual_reports` remains unstated.

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 100%, so baseline would be 3, but the description earns more by explaining parameter interplay that the schema cannot: `report_code` is a value drawn from the list returned when `year` is absent, and the two parameters jointly determine the response shape. `language` and `registry_code` are left to the schema, which is fine given full coverage.

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?

Names the resource precisely ('line items of a company's annual report: balance sheet, income statement, cash flow') and states what values come back (this year and previous year). It is a specific verb+resource, but the no-`year` mode ('lists the available reports') overlaps with the sibling `list_annual_reports` without distinguishing the two, leaving one point of ambiguity.

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

Usage Guidelines4/5

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

Gives explicit conditional usage: omit `year` to enumerate available reports, supply `year` alone to fan out over every report, and supply `report_code` (from the list) for a single one. It also warns that the middle mode costs 'one query each'. No sibling alternative is named, so it stops short of full when-versus-which guidance.

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