Skip to main content
Glama

Conceptfactuur

create_invoice
Destructive

Create a draft invoice or replace an existing draft by ID, then show it to the owner before finalizing; drafts have no number and do not affect the books.

Instructions

Create a draft invoice, or replace one by passing draft_id. A draft has no number and changes nothing in the books. unit_price is excluding btw. vat_code per line: high (21%, the default), low (9%), zero, exempt, eu_reverse_charge (services to a business in another EU country, btw verlegd), outside_eu (services to a customer outside the EU). Under the KOR every line is invoiced without btw automatically. Show the result to the owner before finalize_invoice.

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": {
      "contact_id": "<contact_id>",
      "lines": "<lines>"
    },
    "name": "create_invoice"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNo
linesYes
draft_idNo
contact_idYes
issue_dateNoDefaults to today
supply_dateNoDate the service was delivered, when it differs from the invoice date
payment_term_daysNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=false; the description adds meaning beyond them by explaining that a draft has no number and touches no books, and that KOR forces btw-free lines. It does not spell out that supplying draft_id discards the existing draft's contents or what permissions are needed, which is the residual gap for a destructive mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense and front-loaded: creation semantics first, then the tax-code glossary, then the workflow instruction. Every sentence carries domain information an agent cannot get from the schema, with no filler or repetition of the name.

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 7-parameter destructive mutation with no output schema, the description covers the highest-risk semantics (draft state, btw treatment, tax code choice, the finalize handoff). It omits what the call returns - crucially whether the new draft_id is echoed back, which an agent needs to chain into finalize_invoice - and says nothing about default payment terms.

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 29%, so the description must carry weight, and it does: it defines unit_price as excluding btw and explains every vat_code meaning including eu_reverse_charge ('btw verlegd'), outside_eu, and the implicit kor path. It leaves contact_id, note, payment_term_days, and the quantity unit convention entirely to the schema, so coverage is strong but not complete.

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?

Opens with a specific verb and resource ('Create a draft invoice') and immediately adds the second mode ('or replace one by passing draft_id'), so an agent can distinguish create from update behavior within this tool. It also names finalize_invoice as the next step, separating drafting from the irreversible action.

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 states when to use the replace path (pass draft_id) and routes the agent to finalize_invoice after showing the result to the owner. It does not address adjacent cases such as when to use credit_invoice or send_invoice instead, so it falls short of full alternative coverage.

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