TableJourney food travel

search_places

Read-onlyIdempotent

Search verified venues (read-only). Filter by text, city, kind (a topic such as restaurants, cafes, bakeries, markets, street-food, or a group: eat, drink, bake, do), cuisine, dietary, price tier, opening time, or near a coordinate. Results are ranked by relevance then editorial score and carry provenance (source URL, checked_on, open_status), hours, a page URL to cite and a tracked booking link where one exists. Returns at most limit items; an unknown city returns {did_you_mean: [...]} instead of a list.

Input Schema

TableJSON Schema

Name	Required	Description
`city`	No	City slug or name, e.g. 'new-york-city' or 'New York City'. Unknown cities answer with did_you_mean.
`kind`	No	A topic slug (restaurants, cafes, bakeries, markets, street-food...) or a group: eat, drink, bake, do.
`near`	No	'lat,lng' to search around a point; results then sort by distance.
`limit`	No	Maximum results (1-100).
`query`	No	Free text: a venue name, dish, cuisine, neighbourhood or theme.
`offset`	No	Skip this many results, for paging.
`country`	No	Country slug or name, e.g. 'italy'. Optional where city is given.
`cuisine`	No	Cuisine slug or name, e.g. 'sichuan', 'neapolitan pizza'.
`dietary`	No	vegan, vegetarian, gluten-free, halal, kosher...
`open_at`	No	'now', a weekday and time such as 'sunday 10:00', or an ISO datetime (UTC). Venues with unparseable hours are returned last, flagged.
`radius_km`	No	Radius for near, in km.
`price_tier`	No	The site's tier symbols for the country, e.g. '€€' or '$$$'.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedSep 18, 2026

addedInput schema / properties / city / description

Added value: +"City slug or name, e.g. 'new-york-city' or 'New York City'. Unknown cities answer with did_you_mean."

addedInput schema / properties / country / description

Added value: +"Country slug or name, e.g. 'italy'. Optional where city is given."

addedInput schema / properties / cuisine / description

Added value: +"Cuisine slug or name, e.g. 'sichuan', 'neapolitan pizza'."

addedInput schema / properties / dietary / description

Added value: +"vegan, vegetarian, gluten-free, halal, kosher..."

addedInput schema / properties / kind / description

Added value: +"A topic slug (restaurants, cafes, bakeries, markets, street-food...) or a group: eat, drink, bake, do."

addedInput schema / properties / limit / description
```
Added value: +"Maximum results (1-100)."
```

addedInput schema / properties / near / description

Added value: +"'lat,lng' to search around a point; results then sort by distance."

addedInput schema / properties / offset / description

Added value: +"Skip this many results, for paging."

addedInput schema / properties / open_at / description

Added value: +"'now', a weekday and time such as 'sunday 10:00', or an ISO datetime (UTC). Venues with unparseable hours are returned last, flagged."

addedInput schema / properties / price_tier / description

Added value: +"The site's tier symbols for the country, e.g. '€€' or '$$$'."

addedInput schema / properties / query / description

Added value: +"Free text: a venue name, dish, cuisine, neighbourhood or theme."

addedInput schema / properties / radius_km / description
```
Added value: +"Radius for near, in km."
```

Changed7 schema fields changedSep 18, 2026

addedInput schema / properties / dietary

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Dietary"
+}

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "title": "Offset",
+  "type": "integer"
+}

addedInput schema / properties / open_at

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Open At"
+}

addedInput schema / properties / price_tier

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Price Tier"
+}

addedOutput schema / properties / result / anyOf

Added value: +[
+  {
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  {
+    "additionalProperties": true,
+    "type": "object"
+  }
+]

removedOutput schema / properties / result / items

Removed value: -{
-  "additionalProperties": true,
-  "type": "object"
-}

removedOutput schema / properties / result / type
```
Removed value: -"array"
```

First observedSep 18, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description doesn't need to restate safety. It adds genuinely non-obvious behavior: ranking by relevance then editorial score, result provenance (source URL, checked_on, open_status), hours, tracked booking links, a hard 'limit' cap, and the did_you_mean response for unknown cities. This goes well beyond the annotation baseline.

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?

Three sentences front-load the core purpose and then bundle filters and result characteristics without wasted language. The only minor redundancy is 'read-only' repeating the annotation; otherwise every clause earns its place, though the long second sentence is slightly dense.

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?

The description covers result shape, ranking, unknown-city fallback, and the result cap, and it pairs well with the rich schema and existing output schema. It doesn't explain offset/pagination or how filters combine, but those details are already present in the parameter descriptions, leaving no critical gap for invoking the tool 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?

The input schema has 100% coverage with detailed per-parameter descriptions (including examples for city, kind, open_at, and radius_km). The top-level description summarizes the filter categories but adds no new parameter-level meaning, so the baseline of 3 is appropriate here.

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?

The opening phrase 'Search verified venues (read-only)' names a specific verb and resource, and the description enumerates the full filterable surface (text, city, kind, cuisine, dietary, price tier, opening time, near). It is instantly clear what this tool does and how it differs from siblings like 'place' (a singular lookup) or 'dishes'.

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?

The description clearly frames when to use this tool: when an agent needs to find venues by various criteria and wants ranked, provenance-annotated results. It does not explicitly list sibling alternatives or exclusions (e.g., use 'place' for a single venue by ID), but the resource and filter context is strong enough for an agent to infer the main use case.

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

All TableJourney food travel 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?