Café QR

Add dishes to the menu

add_menu_items

Idempotent

Add dishes to the café's menu, grouped by category, for example from a photo of the printed menu the person shares. Read the photo yourself, show the person the list (categories, names, prices, sizes) and get their OK before calling. Categories are matched by name or created; a dish its category already has is skipped, so calling twice adds nothing. Use sizes for size or portion prices (Regular 3.20, Large 3.80): the dish gets a pick-one Size choice, the cheapest picked already. Use extras for priced add-ons the menu prints (Add cheese 1.00): the dish gets an optional Extras choice. Use spiceLevel 1 to 3 for the chilli symbols printed by a dish. Use price 0 if the photo shows none: the dish is added switched off. Dietary keys: vegetarian (V), vegan (VG), gluten_free (GF), dairy_free (DF), halal (H), spicy (🌶), only where the menu marks them. Allergen keys: gluten, crustaceans, eggs, fish, peanuts, soybeans, milk, nuts, celery, mustard, sesame, sulphites, lupin, molluscs, only where the menu prints them; never guess allergens.

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": {
      "categories": "<categories>"
    },
    "name": "add_menu_items"
  }
}

Input Schema

Name	Required	Description	Default
`cafe`	No	Which café, by name or slug. Only needed when the person has more than one (see list_my_cafes).
`categories`	Yes	Prices are plain numbers in the café's currency, e.g. 3.5 for 3.50.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare it is a non-destructive, idempotent, closed-world write. The description adds substantial behavior beyond that: categories are matched by name or created, duplicate dishes are skipped, price 0 adds the dish switched off, sizes produce a pick-one Size choice defaulting to the cheapest, extras produce an optional Extras choice, and allergens must never be guessed.

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 but nearly every clause carries semantics an agent needs (idempotency, price 0, size default, allergen restraint). The guidance is packed into one long run-on block rather than being broken into scannable points, which slightly hurts front-loading, but there is little filler to cut.

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 nested, two-parameter write with no output schema, the description covers sourcing, confirmation workflow, deduplication, defaults, and every non-obvious field convention. Nothing an agent needs to call it correctly appears to be missing.

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

Parameters5/5

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

Schema coverage is 100%, but the nested fields carry no inline descriptions, so the description supplies the real meaning: sizes vs extras vs plain price, spiceLevel 1-3 mapping to printed chilli symbols, price 0 meaning disabled, and the enumerated dietary and allergen keys with the instruction to use them only where the menu marks them.

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 ('Add dishes to the café's menu, grouped by category') and immediately characterizes the typical source (a photo of the printed menu). An agent can tell this apart from read-side siblings like search_menu or single-item mutators like set_item_sold_out.

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

Usage Guidelines4/5

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

Gives a clear usage workflow: read the photo yourself, show the person the list, get their OK before calling. It also sets an explicit duplicate-handling expectation ('calling twice adds nothing'). It does not explicitly name an alternative sibling for cases like editing an existing dish, so it stops short of full when/when-not routing.

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

All Café QR 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?