Skip to main content
Glama

Overstappen

import_opening_state
Destructive

Set the switch date and import live opening data from another bookkeeping package, including unpaid invoices, asset book values, and last invoice number to continue numbering.

Instructions

Take over what is still alive when the owner switches from another bookkeeping package (Moneybird, e-Boekhouden, Jortt, a spreadsheet). Use it once, after setup_business and after creating the customers with save_contact. It does NOT copy the old administration: the owner keeps an export of the old package for seven years. switch_date: the first day the books are kept here; btw returns and reports start from that day. last_invoice_number: the year and the highest sequence number already used there, so numbering continues without a gap or duplicate (not needed when switching on 1 January). open_invoices: invoices sent from the old package that are not paid yet, with their original number and amounts. They appear as outstanding and can be paid or credited here, but do not count again for turnover or btw. assets: equipment still being depreciated, at its book value on the switch date, with the original purchase price and the remaining years. If the owner uses another package with an MCP server or export, read the figures from there; never estimate them.

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": {
      "switch_date": "<switch_date>"
    },
    "name": "import_opening_state"
  }
}

Input Schema

NameRequiredDescriptionDefault
assetsNo
switch_dateYesFirst day the books are kept in Bookiz, e.g. 2027-01-01. Nothing dated earlier can be booked here afterwards.
open_invoicesNo
last_invoice_numberNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description does not need to restate that this writes. It adds real behavioral context instead: old-administration data is not copied, imported open invoices appear as outstanding but 'do not count again for turnover or btw', and nothing dated before switch_date can be booked afterwards. What is missing is the destruction/irreversibility angle — whether a repeat run duplicates or wipes prior import data, and whether it can be undone — which matters for a tool flagged destructive.

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 and the negative constraint, then one labelled paragraph per parameter. Dense but every sentence carries information; the only soft spot is that the parameter labels are lowercase and run into prose, making the block slightly harder to scan than a bulleted layout.

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?

For a nested, irreversible-feeling import with a 25%-documented schema and no output schema, the definition covers purpose, ordering, source data and per-parameter meaning well. It leaves out what the call returns (counts of imported invoices/assets) and what happens on a partial or repeated import — gaps an agent would want before invoking a destructive tool.

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 only 25%, so the description must carry weight, and it does: each of the four top-level parameters gets meaning beyond the schema — switch_date anchors btw returns and reports, last_invoice_number prevents a gap or duplicate in numbering, open_invoices carry original numbers and must not re-count for turnover, assets are at book value with original price and remaining years. Several nested fields (residual_value, vat_code, contact_id, year/last_used) remain unexplained, which keeps this from a 5.

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 states a specific verb and resource — taking over the still-live opening state when an owner switches from Moneybird, e-Boekhouden, Jortt or a spreadsheet — and explicitly bounds the scope with 'It does NOT copy the old administration'. It also names the siblings it complements (setup_business, save_contact), so an agent can place it without opening any schema.

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?

Ordering is explicit: 'Use it once, after setup_business and after creating the customers with save_contact,' plus a conditional exclusion ('last_invoice_number … not needed when switching on 1 January') and a source-of-truth rule ('read the figures from there; never estimate them'). When-to-use, prerequisites and prohibitions are all present.

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