whitelabel-ordering

Prepare an order

prepare_order

Resolve a natural-language food order (one or more items) to concrete menu items and return a summary plus a confirmation token. Does NOT place the order. Call place_order with the returned token to actually place it. Delivery is as soon as possible by default; pass 'date' to ask for a later time instead. Each call covers one delivery, so an order for more than one day means one call per day. The restaurant may still refuse a time it is not open for.

Input Schema

TableJSON Schema

Name	Required	Description
`date`	No	Delivery date-time as an ISO-8601 UTC instant, e.g. '2026-07-25T12:00:00Z'. Must be in the future. Defaults to 5 minutes from now (as soon as possible) — only pass this when the user asks for a specific time.
`items`	Yes	The item(s) to order — one or more lines, each with an item name, an optional quantity (default 1), an optional size, and optional extra ingredients by name.
`notes`	No	Optional notes for the vendor.
`cutlery`	No	Whether to ask the restaurant to include disposable cutlery. Only pass this when the user says either way; omit to leave it to the restaurant's default. Ignored (with a note) by vendors that do not offer it.
`clientId`	No	clientId of the restaurant, from a list_vendors result. Omit only when the server is configured for a single restaurant.
`vendorId`	No	vendorId of the restaurant, from a list_vendors result. Omit only when the server is configured for a single restaurant.
`bringTerminal`	No	Whether the courier should bring a card terminal so the order can be paid by card on delivery. Pass true when the user wants to pay by card, false for cash; omit when they do not say. Ignored (with a note) by vendors that cannot take card on delivery.
`deliveryAddress`	Yes	Delivery address text, e.g. 'Orlovica Pavla 26'.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 1, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the safety profile is partly covered. The description adds genuinely new behavior: the two-step token handoff to place_order, the ASAP default, the one-delivery-per-call rule, and that the restaurant may refuse an unopened time. It does not explain token expiry or what the summary contains, so it falls short of 5.

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?

Roughly four sentences, each carrying a distinct rule, with the non-placement caveat and the confirmation-token handoff front-loaded. No filler.

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?

For a prepare-then-confirm flow with no output schema, the description supplies the missing return semantics (summary + token) and the follow-up tool, while the schema fully covers every parameter. An agent has everything needed to call it and act on the result.

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?

Schema description coverage is 100%, so the schema already documents all 8 parameters in detail (date default, size rejection, repeat-to-double extras). The description adds only light framing (each call covers one delivery), which is the expected baseline when the schema does the heavy lifting.

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 precise verb+resource: resolve a natural-language food order to concrete menu items and return a summary plus confirmation token. It explicitly distinguishes itself from the sibling place_order, which is the key disambiguation an agent needs here.

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?

Explicit when/when-not: 'Does NOT place the order. Call place_order with the returned token to actually place it.' It also states the default (ASAP delivery), how to override it (pass 'date'), and the one-call-per-delivery constraint.

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

All whitelabel-ordering tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?