Skip to main content
Glama

Prepare a UAE invoice

prepare_invoice

Use this when a user without a connected Fatura Go account asks to make, prepare or calculate an invoice for a client. Checks an invoice and works out its totals with UAE VAT rules (line rounding, 5% standard rate, full or simplified tax invoice, AED amounts), lists what is still missing under Article 59, and returns a link that opens the invoice in the Fatura Go invoice generator on invoicefatura.com, where the user can review it and download a PDF. When no card is shown, show the user the lines and totals from the result before the link. Nothing is issued or sent, and no invoice number is assigned. The link works for 24 hours. Use only details the user gave; leave a TRN out rather than guess it. No email addresses or phone numbers. For someone who has connected their own Fatura Go account, use create_draft_invoice from that connection instead: it saves a draft in their account. Do not use it for a connected user: save a draft with create_draft_invoice instead. It does not send or issue an 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": {
      "client": "<client>",
      "lines": "<lines>"
    },
    "name": "prepare_invoice"
  }
}

Input Schema

NameRequiredDescriptionDefault
linesYes
notesNo
clientYesThe customer being invoiced.
sellerNoThe user's own business.
currencyNoDefault AED.
due_dateNoYYYY-MM-DD; default 14 days after the invoice date (Net 14).
languageNoInvoice language; default en.
invoice_dateNoYYYY-MM-DD; default today (UAE).
prices_include_vatNotrue when unit prices already include VAT.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, it discloses a lot: nothing is issued or sent, no invoice number is assigned, the link expires in 24 hours, Article 59 gaps are reported, and the agent should surface lines and totals when no card renders. Those are operational facts an agent cannot infer from readOnlyHint/destructiveHint alone.

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

Conciseness3/5

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

The trigger and the main constraint are front-loaded, but the connected-user exclusion is stated twice in near-identical wording ('use create_draft_invoice instead' and 'Do not use it for a connected user'), and 'It does not send or issue an invoice' repeats the earlier 'Nothing is issued or sent.' Roughly a fifth of the text is redundant.

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 return-value burden and does: a link to the generator, the computed lines/totals, the list of Article 59 gaps, and a 24-hour expiry. Combined with the nested client/seller/lines schema, an agent has everything needed to call it and explain the result.

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 already 78%, and the description still adds policy-level meaning: UAE VAT rules with line rounding and 5% standard rate, AED amounts, full vs simplified tax invoice, and the omit-a-TRN rule that reinforces the schema's guidance. It doesn't walk through every parameter (e.g. prices_include_vat, language, due_date defaults), so it stops short of full compensation.

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 names a specific verb and resource ('prepare or calculate an invoice for a client') and scopes it to UAE VAT invoices returned as a generator link. It also explicitly contrasts itself with create_draft_invoice, so an agent can distinguish the two without opening either 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?

It gives an explicit trigger ('a user without a connected Fatura Go account'), an explicit exclusion ('For someone who has connected their own Fatura Go account, use create_draft_invoice'), and data-handling rules (only user-supplied details, omit rather than guess a TRN, no email/phone). Alternatives and when-not conditions are both stated.

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