Skip to main content
Glama

IQ Books by ReconcileIQ

Start a set of books

set_opening_balances
Destructive

Enter the opening trial balance for a new set of books, once per set. Call with no lines to see whether these books can still take them and the rules; with lines to preview the trial balance; with the token to post. Enter opening debtors and creditors as the outstanding invoices and bills themselves where you can, so aged reports and statements can show them. A lump figure is allowed (a migration brings one for old balances), but money in a control account with no document behind it never appears on an aged report or statement. Never do both for the same debt: it would count twice.

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": "set_opening_balances"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_atNoThe day before trading starts in these books. Usually the old system's last day.
linesNoThe opening trial balance, one line per account: the account (code or exact name) and a debit or a credit in pounds. Debits and credits must balance.
descriptionNoA note saved on the opening balance journal, e.g. "Opening balances from Xero".
lock_periodNoLock everything up to as_at once the balances are in, so nothing can be posted behind them. Default true, and it is the right default.
organisation_idNoWhich books. Leave it out to use the books chosen with select_organisation, or the only set this account has.
confirmation_tokenNoLeave it out to preview. To carry the change out, send the token the preview returned, unchanged.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / confirmation_token / description
      Added value: +"Leave it out to preview. To carry the change out, send the token the preview returned, unchanged."
    • addedInput schema / properties / description / description
      Added value: +"A note saved on the opening balance journal, e.g. \"Opening balances from Xero\"."
    • addedInput schema / properties / lines / description
      Added value: +"The opening trial balance, one line per account: the account (code or exact name) and a debit or a credit in pounds. Debits and credits must balance."
    • addedInput schema / properties / organisation_id / description
      Added value: +"Which books. Leave it out to use the books chosen with select_organisation, or the only set this account has."
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=false; the description goes further and explains the concrete consequences: lock_period locks everything up to as_at, a lump figure without a document never shows on aged reports or statements, and double-entry of a debt counts twice. That is exactly the risk context a destructive mutation needs.

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 the core action and the mode contract, then the debtors/creditors advice. Dense and mostly waste-free, though the invoice-versus-lump discussion is a long clause chain that could be tightened without losing meaning.

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?

For a destructive, no-required-param, no-output-schema tool, the description supplies the full workflow (check → preview → post), the locking consequence, and the data-quality traps. Nothing material an agent needs before invoking it is missing.

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 the baseline is 3, but the description adds real semantics the schema does not: the mode-selection meaning of omitting or supplying lines and confirmation_token, and the guidance to use outstanding invoices/bills rather than control-account lumps. It does not cover as_at, description, or lock_period, which the schema handles.

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: 'Enter the opening trial balance for a new set of books, once per set.' No sibling in the list covers opening balances, and the 'once per set' scope plus the three-mode calling convention make it unmistakable.

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

Usage Guidelines5/5

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

Explicitly maps each usage mode to an input state: no lines = eligibility check and rules, lines = preview, token = post. It also gives accounting-level guidance on when to enter invoices/bills versus a lump figure, and the hard exclusion ('Never do both for the same debt').

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