Skip to main content
Glama

Change a draft quote

update_draft_quote
DestructiveIdempotent

Use this when the user asks to change a draft quote or proforma invoice. Changes a draft quote or proforma: only the fields passed change; items replaces all lines. Sent quotes cannot be changed here. Line descriptions are printed on the tax invoice: write them in English, translating when the user writes in another language (for example "Консультация" becomes "Consultation"). Keep names, brands and model numbers exactly as written. Use another language only when the user explicitly asks for it or quotes the exact text. Lines are priced by Fatura Go as in the app (each line rounded, header = sum of lines; with prices_include_vat the entered price includes VAT, e.g. 26.95 = 25.67 + 1.28 VAT). Returns the stored lines and totals and app_url. Nothing is issued, numbered as a tax invoice or sent: the user reviews and issues it in Fatura Go ("Review and issue in Fatura Go"). Do not use it for a new quote (create_draft_quote) or a quote already sent.

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": {
      "quote_id": "<quote_id>"
    },
    "name": "update_draft_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoYYYY-MM-DD. Default today (UAE).
itemsNoThe lines, 1 to 100. On an update they replace every line.
notesNo
currencyNoOne of AED, SAR, USD, EUR, GBP, KWD, QAR, BHD, OMR, INR. Default the client's preferred currency, else the business currency.
quote_idYesFrom create_draft_quote or list_quotes (status draft).
client_idNoFrom list_clients or create_client.
business_idNoFrom list_businesses. May be left out when the connection shares exactly one business.
client_nameNoOnly when the client_id is not known: nothing is written, and the matching clients are returned to pick from.
valid_untilNoYYYY-MM-DD, on or after date.
idempotency_keyNoOptional. A unique string (for example a UUID) for this request: a retry with the same key returns the first result instead of writing again.
prices_include_vatNoWhether unit_price includes the 5% VAT. Default the business setting.
document_language_overrideNoLanguage this document prints in: en, ar or bilingual. Left out: a new draft follows the business setting and an update keeps the current choice; null goes back to the business setting. Only for a document the user asked to print in another language.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / document_language_override
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 20,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Language this document prints in: en, ar or bilingual. Left out: a new draft follows the business setting and an update keeps the current choice; null goes back to the business setting. Only for a document the user asked to print in another language."
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description corroborates rather than contradicts: 'items replaces all lines', 'sent quotes cannot be changed here', and 'Nothing is issued, numbered as a tax invoice or sent'. It also discloses pricing/rounding behavior (each line rounded, header = sum of lines, VAT-inclusive interpretation) which annotations cannot convey. It does not, however, mention the idempotency_key retry semantics that the annotation implies, so it is not fully exhaustive.

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?

Dense and front-loaded: trigger first, then mutation semantics, then the printing/language rule, then pricing, then the return value and the not-issued caveat. Every sentence carries information, though the English-translation guidance given here is repeated from the schema, adding some redundancy.

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?

With 12 parameters, no output schema, and destructive semantics, the description does the work that structure cannot: it explains what is replaced, what is left untouched, that nothing is issued or numbered, and that the response returns stored lines, totals and app_url. There is no output schema, and the description still summarizes returns, which is more than required.

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 92%, so the schema already carries most parameter meaning and baseline is 3. The description adds genuine semantics beyond it: the VAT-inclusive price arithmetic worked through with a concrete figure (26.95 = 25.67 + 1.28) and the language/transliteration rule for line descriptions. The language rule is largely duplicated from the schema's description field, which caps it below 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?

Specific verb plus resource ('Changes a draft quote or proforma'), states the update semantics ('only the fields passed change; items replaces all lines'), and draws a hard boundary at sent quotes. An agent can distinguish it from create_draft_quote by name in the closing sentence.

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?

Opens with an explicit trigger ('Use this when the user asks to change a draft quote or proforma invoice'), then lists exclusions: not for a new quote (routes to create_draft_quote) and not for a quote already sent, and adds the follow-up path ('Review and issue in Fatura Go'). Both when and when-not are covered with named alternatives.

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