Skip to main content
Glama

LoafLoaf Toronto Restaurants

search_restaurants

Read-onlyIdempotent

Find restaurants around a location, with Google's filters plus a per-person budget.

Each result has a place_id, rating, price range, distance, whether it is open now and any awards. excluded counts places dropped by the filters and why. Next: get_restaurant(place_id) for hours, booking and ordering links; get_menu(place_id) for the menu.

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": {
      "near": "<near>"
    },
    "name": "search_restaurants"
  }
}

Input Schema

NameRequiredDescriptionDefault
nearYesThe user's location: 'lat,lng' coordinates, a postal code ('M6J 1G1'), an address, an intersection ('Queen and Ossington') or a neighbourhood ('Little Italy').
sortNorelevance
limitNo
queryNoFree text Google matches against places, e.g. 'tapas', 'patio', 'date night', 'tasting menu'.
cuisineNoCuisine or kind of place: 'italian', 'korean bbq', 'sushi', 'ramen', 'steak house', 'cafe', 'bar', 'vegan'. Matched to Google's place types when one exists.
open_atNoOpen at a local day and time, e.g. 'fri 19:30' or 'saturday 11am'.
featuresNoAttributes that must all be true, e.g. ['reservable', 'outdoor_seating'].
open_nowNo
radius_mNoHard limit on distance, metres.
budget_maxNoPer person, CAD. Compared with Google's per-person price range (e.g. '$50-100').
budget_minNoPer person, CAD.
min_ratingNo
min_reviewsNo
price_levelsNoGoogle price levels to keep: 1=$ 2=$$ 3=$$$ 4=$$$$.
include_unknown_priceNoWith a budget, also keep places Google has no price range for.

Output Schema

NameRequiredDescriptionDefault
notesYes
pagesNo
filtersYes
resultsYes
scannedNo
excludedYes
locationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description does add genuine value by previewing result fields (place_id, rating, price range, distance, open-now, awards) and disclosing the `excluded` diagnostic that counts filtered-out places and the reason. It says nothing about result ordering behavior, result cap behavior beyond the schema, or cost/latency of the open-world lookup.

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 core purpose in one sentence, then return shape, then next-step routing. Three short, non-redundant blocks with no filler, though the trailing 'Next:' sentence mixes in output-preview content already covered by the output schema.

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?

With 15 parameters and an output schema present, the description does the right high-level framing and does not need to restate return values. The main residual gap is the undocumented filter parameters that neither schema nor description explain, which matters for a filter-heavy search tool.

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 67%, so several parameters (sort, limit, open_now, min_rating, min_reviews) carry no documented meaning anywhere. The description only frames the parameter space at a high level ('Google's filters plus a per-person budget') and adds no syntax, interaction, or edge-case detail beyond what the schema already states.

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 description opens with a specific verb and resource ('Find restaurants around a location') plus the scope qualifier that defines it: Google's filters combined with a per-person budget. It clearly separates itself from get_restaurant and get_menu by routing those follow-ups explicitly, but the sibling find_restaurant is never mentioned, so the search-vs-find boundary is left ambiguous.

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?

Usage context is clear (location-anchored search with filters and budget) and it gives concrete next-step routing: get_restaurant(place_id) for hours/booking/ordering and get_menu(place_id) for the menu. There is no explicit 'do not use this for X' exclusion or a stated alternative for name-only lookups, which keeps it from 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