Skip to main content
Glama

Uitgave boeken

record_expense

Book a business purchase from a receipt or invoice, capturing VAT treatment, category, and payment source while blocking likely duplicates.

Instructions

Book a business purchase from a receipt or purchase invoice. amount is the total paid including btw; vat_amount is the btw printed on the document (required for Dutch suppliers, 0 if none is shown). vat_treatment: nl (Dutch supplier, the default), eu_reverse_charge (supplier in another EU country charged no btw, e.g. Google Ireland), non_eu_reverse_charge (supplier outside the EU, e.g. a US SaaS), none (no btw involved: private seller, exempt, insurance). paid_from: business account, or private when the owner paid with private money. kind: investment for a durable asset of €450 or more excluding btw (laptop, camera); it is depreciated over useful_life_years (default 5). category: kantoor (papier, postzegels, kleine apparatuur, flexplek); software (SaaS, domeinnaam, hosting, AI-abonnement); telefoon_internet (alleen het zakelijke deel); reiskosten (trein, parkeren, taxi; eigen auto via kind "mileage"); opleiding (cursus, boeken voor het vak); verzekering (beroepsaansprakelijkheid; geen arbeidsongeschiktheidsverzekering); marketing (advertenties, website, drukwerk); advies (boekhouder, jurist, Bookiz); bankkosten (zakelijke rekening, betaalprovider); representatie (relatiegeschenk, congres, zakelijke lunch die je zelf inkoopt); eten_drinken_horeca (zakelijke lunch of diner in restaurant of café); overig (alles wat nergens anders past). Refuses a likely duplicate unless allow_duplicate is true. Afterwards, store the original with attach_receipt.

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": {
      "date": "<date>",
      "vendor": "<vendor>",
      "amount": "<amount>"
    },
    "name": "record_expense"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYesCalendar date, YYYY-MM-DD
kindNo
amountYesAmount in euros, at most two decimals, e.g. 121.00
vendorYes
categoryNo
paid_fromNo
vat_amountNoAmount in euros, at most two decimals, e.g. 121.00
descriptionNo
vat_treatmentNo
residual_valueNoAmount in euros, at most two decimals, e.g. 121.00
allow_duplicateNo
useful_life_yearsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare readOnly=false, destructive=false and openWorld=false, so the description has to carry the rest, and it does: it discloses duplicate refusal, the Dutch-supplier VAT requirement, reverse-charge handling for EU and non-EU suppliers, and that investments are depreciated over useful_life_years. It does not describe error conditions or what a successful booking returns, but the behavioral picture is substantially richer than the annotations.

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?

The opening two sentences front-load the core semantics, and the category list, while long, carries genuine routing information that is not in the schema. The single sprawling sentence with nested parentheses is heavy to parse and the erroneous "mileage" note is wasted noise, but there is little outright padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter mutation tool with no output schema and 33% schema coverage, key gaps remain: what the description field is for, what residual_value means for investments, and what a successful booking yields before attach_receipt is called. The VAT and category guidance is strong, but the definition is not fully complete for the tool's complexity.

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?

With schema coverage at 33%, the description usefully disambiguates vat_amount, vat_treatment, paid_from, category, kind, useful_life_years and allow_duplicate, which is real added meaning. However it instructs using kind "mileage" for own-car travel even though the schema enum is only cost/investment, which would lead an agent to submit an invalid value; vendor, description and residual_value also get no semantic treatment.

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?

"Book a business purchase from a receipt or purchase invoice" gives a specific verb plus resource, and the closing line routes the agent onward to attach_receipt, which separates this from the invoice-side siblings. The overall intent is unambiguous without opening the schema.

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?

It spends most of its length on how to choose between the enumerated options for vat_treatment, kind, paid_from and category, and it states the duplicate-check behaviour plus the allow_duplicate escape hatch. What is missing is an explicit statement of when NOT to use this tool (e.g. own-car mileage belongs to record_mileage, invoices to create_invoice) beyond a passing mention of kind "mileage".

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