Skip to main content
Glama

Search dishes

search_dishes
Read-onlyIdempotent

Search dishes on Sydney restaurant and cafe menus and see which are free of allergens. Write the query the way a person would say it: 'gluten free pasta warriewood', 'nut free thai inner west', 'coeliac friendly brunch bondi', 'vegan dumplings surry hills'. Allergen, diet and place words are understood, and so are things a table needs from the venue: 'dog friendly', 'kid friendly', 'outdoor seating', 'private room for 12', 'set menu', 'group bookings', 'harbour view', 'rooftop', 'takes bookings', 'walk in only', 'baby change', 'wheelchair accessible'. Those are hard filters (all of them must hold, as on the website): only venues whose own data says yes are returned, a venue that has not said is never counted, and a party size with a private room leaves out rooms that print a smaller capacity. Each dish shows its status per allergen (free by default, or can be made free with what to ask for, such as 'GF pasta +$4'), the venue, a link, and the day the menu was read.

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": {
      "query": "<query>"
    },
    "name": "search_dishes"
  }
}

Input Schema

NameRequiredDescriptionDefault
nearNoOptional place name: a Sydney suburb or region, such as 'Manly' or 'Inner West'. Suburbs and regions mean within 4 km, nearest first. Coordinates as 'lat,lng' also work.
exactNoSkip spelling correction.
limitNoDishes to return. Default 12.
queryYesWhat to eat, in plain words, including allergens and place. Example: 'gluten free pizza manly'.
free_ofNoOptional. Allergens every dish must be free of, free by default or able to be made free: gluten, dairy, nuts, peanut, treenut, egg, soy, sesame, shellfish, fish, seafood, lupin, sulphite. 'coeliac' means gluten. Diets vegetarian and vegan also work.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / near / description
      Previous value: -"Optional. A Sydney suburb or region to search around ('Manly', 'Inner West'), or 'lat,lng'. Suburbs and coordinates mean within 4 km, nearest first."New value: +"Optional place name: a Sydney suburb or region, such as 'Manly' or 'Inner West'. Suburbs and regions mean within 4 km, nearest first. Coordinates as 'lat,lng' also work."
  2. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real value beyond them: hard-filter semantics (all must hold, unstated data never counts, party size vs private room capacity), the 'can be made free' status with an upsell note ('GF pasta +$4'), and the 'day the menu was read' freshness signal.

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?

Purpose is front-loaded in the opening sentence and the following sentences carry distinct payloads (query phrasing, hard-filter rule, return shape). The long enumeration of amenity phrases ('dog friendly', 'baby change', 'walk in only'...) is useful but is the one padded stretch that could be trimmed without loss.

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?

There is no output schema, and the description compensates by spelling out the return shape: per-allergen status, venue, link and menu-read date. Combined with the hard-filter rule and query phrasing guidance, an agent has everything needed to call it correctly.

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?

With 100% schema description coverage, the schema already documents near, exact, limit, query and free_of, so the baseline is 3. The description reinforces query phrasing and clarifies that free_of accepts 'free by default or able to be made free' and that 'coeliac' means gluten, but it says nothing about near, exact or limit, which remain schema-only.

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?

The first sentence names a specific verb and resource ('search dishes on Sydney restaurant and cafe menus') and adds the differentiator that results are allergen-annotated. Scope is unambiguous, but it never names or rules out the siblings list_allergen_free or compare, leaving an agent to infer the boundary from names alone.

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?

Strong practical guidance on how to call it: write the query conversationally, with four concrete example queries, plus an explicit list of amenity words that are treated as hard filters. It lacks any when-not-to-use or explicit alternative routing, so it stops short of a 5.

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