Skip to main content
Glama

Lokand Restaurant MCP

Add item

add_item

Add a dish/item to a menu (optionally inside a category). Returns the new item_id.

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": {
      "menu_id": "<menu_id>",
      "name": "<name>"
    },
    "name": "add_item"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoOptional caller-chosen id (8-64 chars). Reuse the same id when retrying so a retry can never create a duplicate.
nameYesItem name, e.g. "Cacio e pepe"
priceNoPrice in the business's currency. Required unless `variations` is given, in which case it is derived from the cheapest variation.
menu_idYes
sort_orderNo
variationsNoVariations of this dish — sizes, volumes, portions, cuts — each with its own ABSOLUTE price (not a surcharge): e.g. [{name:'Small',price:3},{name:'Large',price:4.5}]. Use this instead of creating one item per variation. The item's own `price` becomes the 'from' price (the cheapest variation) automatically, so you may omit `price` when you pass variations. Names must be unique.
category_idNo
descriptionNo
dietary_infoNoAllergen and dietary labels shown to diners. `allergens` uses the 14 standard codes (gluten, crustaceans, eggs, fish, peanuts, soybeans, milk, nuts, celery, mustard, sesame, sulphites, lupin, molluscs); `contains` flags alcohol, pork or tobacco; `suitableFor` carries positive claims (vegetarian, vegan, halal, ...); `caloriesKcal` and `portionGrams` are per portion. Optional `declaredAt` (epoch-ms) records that a dish was reviewed, which sharpens check_compliance — a dish with no allergens and no declaredAt is indistinguishable from one nobody has looked at yet.
is_availableNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is known. The description adds the useful fact that a new item_id is returned, but says nothing about auth/permission requirements or side effects (e.g. whether price is derived from variations, whether the item appears immediately on a live menu).

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?

Two short sentences, front-loaded with the action and scope, and ending with the return value. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The return value is covered despite there being no output schema, which is the main gap a description must fill here. But for a 10-parameter nested mutation tool it is thin: idempotency/retry behavior, price-vs-variations interaction and any permission constraints are left entirely to the schema or unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 10 parameters, nested objects and only 50% schema description coverage, the description must compensate and does not. It only clarifies that category placement is optional — which the schema's required list already shows — and adds no meaning for price derivation, variations, dietary_info, sort_order or the retry-safe id.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb+resource: "Add a dish/item to a menu", with the scope note that a category is optional and the return value (new item_id) named. It is clearly distinct from delete_item/update_item by verb, but it never names a sibling or distinguishes itself from add_category/add_block-style tools explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the verb and the parenthetical "optionally inside a category" hints at the category_id choice, but there is no when-to-use/when-not guidance, no mention of prerequisites (menu must exist, permissions), and no pointer to update_item for later edits or to variations instead of duplicate items.

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