Skip to main content
Glama

Check the VAT treatment of a supply

check_vat_on_supply
Read-onlyIdempotent

Use this when the user asks whether to charge 5% VAT, 0% or no VAT on a sale: to a client abroad, in a free zone or in the GCC, on exports of goods or services, or for property, education or healthcare. Says whether a UAE supply is standard-rated (5%), zero-rated, exempt or out of scope, from what is supplied (goods or services, or a special category such as residential property, education or international transport), where the customer is (country, UAE free zone) and, for exports, the facts zero rating depends on (goods leaving within 90 days and the evidence; for services the customer's residence and presence, the 30-day rule and whether a visit was connected with the work, connection with UAE real estate or goods, the special place-of-supply rules). Each step cites the article, and a zero rate comes with the conditions and records needed to keep it. When a deciding fact is missing the result is "depends" with the questions to ask: ask the user, do not assume. Do not use it to calculate an amount (calculate_vat) or for registration (check_vat_registration).

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": {
      "supply": "<supply>"
    },
    "name": "check_vat_on_supply"
  }
}

Input Schema

NameRequiredDescriptionDefault
supplyYes
categoryNoA special category, if any. Default general.
export_evidenceNo
customer_countryNoISO 3166 two-letter code of where the customer is, for example AE, GB, SA.
export_arranged_byNoGoods: who arranges transport out of the UAE.
performed_outside_uaeNoServices: the work is actually carried out outside the UAE.
special_place_of_supplyNo
connected_to_goods_in_uaeNo
customer_in_uae_free_zoneNo
goods_located_outside_uaeNoGoods: supplied abroad and never brought into or sent from the UAE.
customer_has_uae_residenceNoServices: the customer has a business, branch or residence in the UAE.
days_in_uae_last_12_monthsNoDays the customer (or the person receiving the work) was in the UAE over the 12 months before the supply.
goods_into_designated_zoneNo
connected_to_uae_real_estateNo
goods_exported_within_90_daysNo
customer_in_uae_when_performedNo
presence_connected_with_supplyNoAny time the customer spent in the UAE was connected with this work (meetings, workshops).
received_in_uae_by_another_personNoAn employee, director or branch of the customer receives the work in the UAE.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety needs no restating. The description adds real behavioral context beyond them: each step cites the article, zero-rating results come with the conditions and records needed to keep them, and incomplete inputs yield a 'depends' verdict with follow-up questions instead of a guess.

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 the trigger question before any detail, and no filler sentences — every clause concerns a real decision factor. It is dense and runs long with nested parentheticals, which slightly hurts scannability, but nothing is redundant.

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 an 18-parameter, no-output-schema tool in a rule-heavy domain, the description explains the shape of the answer (article-cited reasoning, conditions attached to zero rates, 'depends' plus questions) and the input axes. Minor gaps remain around a few edge-case flags, but an agent has enough to call it and use the result correctly.

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?

With 18 parameters at 50% schema coverage, the description carries meaningful weight: it explains the decision axes (goods vs services or a special category, customer country and free zone, export evidence, 90-day removal, the 30-day presence rule, visit connected with the work, connection to UAE real estate or goods, special place-of-supply rules) that map onto the mostly undocumented booleans. A few flags, such as goods_into_designated_zone and received_in_uae_by_another_person, are only obliquely implied.

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?

States a specific verb and resource — deciding the VAT treatment (standard-rated 5%, zero-rated, exempt, out of scope) of a UAE supply — and enumerates the fact patterns it covers (client abroad, free zones, GCC, exports, property, education, healthcare). It explicitly differentiates itself from calculate_vat and check_vat_registration, so an agent can route 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?

Opens with the exact user question that should trigger it ('whether to charge 5% VAT, 0% or no VAT'), then gives explicit exclusions naming the sibling tools for calculation and registration. It also specifies behavior when facts are missing: return 'depends' with questions and ask the user rather than assume.

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