Skip to main content
Glama

Evendo Places

Find venues in a place

find_venues
Read-only

List venues of one type anywhere inside a place (country, region, city or neighbourhood), best-ranked first, or nearest-first when near is given; sort_by switches to highest rated, most reviewed or distance. Use for requests like 'top-rated cheap Italian restaurants in Prague', 'most reviewed bars in London' or 'family-friendly outdoor attractions in Scotland'. place_id must come from resolve_place. For keyword matching ('sushi', 'rooftop', 'craft beer'), use search_venues instead. If a neighbourhood returns fewer than ~5 results, widen to its city.

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": {
      "place_id": "<place_id>",
      "venue_type": "<venue_type>"
    },
    "name": "find_venues"
  }
}

Input Schema

NameRequiredDescriptionDefault
nearNoRestrict to this radius around a point; results then sort nearest-first unless sort_by says otherwise. For 'near <landmark>', first find the landmark with search_venues (venue_type Landmarks, then Attractions) and use its location.
limitNoResults per page.
accessNoPhysical access difficulty. Every listed value must be present (AND), so pass only what the user actually requires.
cursorNonext_cursor from a previous call with otherwise identical arguments. Never invent one.
sort_byNobest (default): Evendo ranking, or nearest-first when `near` is given. place_score: highest Evendo place score (0-100 overall quality) first. rating: highest average rating first (pair with min_reviews so 1-review places don't win). reviews: most reviewed first ('most popular'). nearest / farthest: by distance, require `near`. Places missing the value sort last. Changing sort_by restarts pagination: don't reuse a cursor from another sort.
ambienceNoAtmosphere tags. Every listed value must be present (AND), so pass only what the user actually requires.
audienceNoWho the place suits / accessibility. Every listed value must be present (AND), so pass only what the user actually requires.
categoryNoExact, case-sensitive category. Restaurants: "Italian", "Japanese", "Mexican", "Indian", "Chinese", "Thai", "French", "Mediterranean", "Seafood", "Steakhouse", "Pizza", "Sushi", "Vegan", "Vegetarian", "Fast Food", "Fine Dining". Bars: "Cocktail Bar", "Wine Bar", "Sports Bar", "Beer Garden". Shopping: "Market", "Boutique", "Mall". Attractions: "Museum", "Park", "Gallery", "Zoo", "Theme Park", "Garden". If unsure of the exact value, use search_venues text instead.
place_idYesID from resolve_place.
amenitiesNoRequired amenities. Every listed value must be present (AND), so pass only what the user actually requires.
experienceNoExperience tags. Every listed value must be present (AND), so pass only what the user actually requires.
min_ratingNoMinimum average rating, 0-5. "good" = 4.0, "top rated"/"best" = 4.5 (pair with min_reviews).
venue_typeYesRestaurants (incl. cafes, diners), Bars (pubs, nightclubs), Shopping (markets, shops), Attractions (museums, parks, galleries, zoos), Landmarks (monuments, historic sites). Unsure between Attractions and Landmarks? Try both.
environmentNo"outdoor"/"terrace"/"al fresco" = Outdoor. For "outdoor seating" make two calls, Outdoor and "Indoor and Outdoor", and merge.
min_reviewsNoMinimum number of reviews; use ~50+ to avoid thinly-rated places. "good" = 10+, "top rated" = 20+.
price_levelNo"cheap"/"budget" = inexpensive; "upscale"/"fancy" = expensive or very_expensive. There is no "free" level; for free places use search_venues with text "free".
style_visualNoViews. Every listed value must be present (AND), so pass only what the user actually requires.
location_typeNoFiner type than venue_type, exact match, e.g. "Pub", "Cafe", "Restaurant", "Attraction", "Gastropub", "Museum". Pub = Bars + "Pub"; cafe / coffee shop = Restaurants + "Cafe".
sustainabilityNoSustainability tags. Every listed value must be present (AND), so pass only what the user actually requires.
min_place_scoreNoMinimum Evendo place score (0-100 overall quality; most venues are 20-50, 70+ is excellent, 90+ is a city's very best).
style_aestheticNoInterior / design aesthetic. Every listed value must be present (AND), so pass only what the user actually requires.
style_architectureNoArchitecture. Every listed value must be present (AND), so pass only what the user actually requires.
style_social_mediaNoPhoto / social-media appeal. Every listed value must be present (AND), so pass only what the user actually requires.
weather_suitabilityNoWeather suitability. Every listed value must be present (AND), so pass only what the user actually requires.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries real weight and does add value: it discloses the default ranking (Evendo best-rank, nearest-first when `near` is supplied) and the ~5-result neighbourhood widening rule. Much of the remaining behavioral detail (pagination restart on sort change, missing-value sort ordering) sits in the schema rather than the description, which keeps it just under full marks.

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-loads the core behavior, then examples, then routing and the fallback heuristic — a logical order with no filler. It is dense but every clause carries information; the only mild redundancy is restating the sort_by switch already covered in the schema.

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 24-parameter discovery tool with no output schema, the description supplies what an agent needs to call it correctly: provenance of the required place_id, default ordering, the alternative tool for text search, and a recovery path for sparse results. The sibling get_venue/get_venues presumably cover result detail, so not describing the return shape is acceptable here.

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% and the schema already documents every parameter in depth, including near, sort_by, cursor and the enum semantics. The description adds only the place_id provenance and the near/sort interaction at a high level, so it lands at the baseline for a fully-documented schema.

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 ("List venues of one type anywhere inside a place") plus the geographic granularity (country, region, city, neighbourhood) and the default ordering. It explicitly contrasts itself with search_venues for keyword matching, so an agent can distinguish the two without opening either schema.

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?

Gives an explicit prerequisite (place_id must come from resolve_place), an explicit exclusion routing to search_venues for keyword matching, and a concrete fallback heuristic (widen a thin neighbourhood result set to its city). The three worked example requests anchor when-to-use in real phrasing.

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.