Skip to main content
Glama
easor

easor

by Markku-hur

Build tase (balance sheet) as of a date

build_balance_sheet
Read-only

Builds a fully computed balance sheet (Tase) as of a given date with real euro totals, current-period result, balance-mismatch detection, and separate unclassified accounts.

Instructions

Builds a fully-computed Tase as of the given date — VASTAAVAA (assets) and VASTATTAVAA (equity + liabilities), every official line with real activity (lines with no activity at all are omitted) and real euro figures, cumulative since inception (no period math needed for a balance-sheet account). Both sides are shown as positive figures (conventional presentation sign, NOT raw ledger signs) — a balanced Tase means EQUAL totals on both sides. The fiscal year's not-yet-closed result is included in OMA PÄÄOMA under Tilikauden voitto (tappio) and also returned as currentPeriodResult, so a mid-year Tase balances too. Use this instead of assembling a report by hand from lookup_chart_of_accounts_template — it always produces the same structure. balanceMismatch is non-null if the two sides don't match (a Tase must balance) — surface that to whoever asked rather than reporting an unbalanced tase as if it were fine. Any account the organization uses that isn't recognized by the bundled template is listed separately in unclassifiedAccounts (raw ledger sign there, not the presentation sign above), never silently folded into a line.

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": {
      "organizationNumber": "<organizationNumber>",
      "asOfDate": "<asOfDate>"
    },
    "name": "build_balance_sheet"
  }
}

Input Schema

NameRequiredDescriptionDefault
asOfDateYesYYYY-MM-DD
organizationNumberYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial context beyond them: sign convention is presentation-positive rather than raw ledger, the unclosed fiscal-year result is folded into OMA PÄÄOMA and also returned as currentPeriodResult, and empty lines are omitted. It also discloses the key failure surface — balanceMismatch must be surfaced to the requester, and unknown accounts go to unclassifiedAccounts in raw ledger sign — which is exactly the kind of behavioral detail annotations cannot convey.

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, then progressively adds sign conventions, mid-year balancing, and error handling — a sensible order for a complex financial tool. It is dense but nearly every clause carries information; only minor parenthetical asides ('a Tase must balance') are restatement rather than new content.

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?

There is no output schema, so the description carries the full return-value burden and does so: named sections, the currentPeriodResult field, balanceMismatch, and unclassifiedAccounts with its differing sign convention. For a computed financial report with two parameters, an agent has everything needed to call it and interpret the result.

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 50%: asOfDate is documented in the schema as YYYY-MM-DD while organizationNumber is undocumented in both places. The description contributes meaningful semantics for asOfDate by clarifying it acts as a cutoff over cumulative-since-inception figures, but it says nothing about what organizationNumber expects or whether it must match a configured organization. Baseline 3 given partial schema coverage.

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 ('Builds a fully-computed Tase as of the given date') and immediately defines scope: VASTAAVAA and VASTATTAVAA, cumulative since inception. It names the sibling it replaces ('use this instead of assembling a report by hand from lookup_chart_of_accounts_template'), so an agent can distinguish it from build_profit_and_loss_statement or the chart-of-accounts lookups.

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?

Explicitly directs the agent away from the manual alternative and states the invariant case ('no period math needed for a balance-sheet account'). It does not state when NOT to use it (e.g., versus build_profit_and_loss_statement for period results), but the routing context is clear enough to act on.

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