Yenta Directory

Search venues

search_venues

Read-onlyIdempotent

Search published venues by name or description, optionally filtered by city, cuisine, price band, neighbourhood, whether the venue takes reservations, proximity (near a lat/long within a radius, nearest first) and opening hours (open on a given day/time, or open now) — all HARD filters that exclude on a miss, plus a HARD experiential-facet filter (facets, ':' tokens from facet_vocabulary) — with prefer_cuisine, prefer_neighbourhood, avoid and prefer_facets as SOFT preferences that only rank a venue up or down and never drop it; each result carries the venue's capabilities and, when it is live, its mcp_endpoint.

Input Schema

TableJSON Schema

Name	Required	Description
`at`	No	A 24-hour HH:MM time; with open_on, require the venue be open then.
`city`	No	Only return venues in this city (case-insensitive); call list_cities for the exact values this directory knows.
`near`	No	Only return venues within radius_km of this 'latitude,longitude' point, nearest first, each with a distance_km; venues with no coordinates are excluded.
`avoid`	No	Soft preference: venues matching these cuisine/neighbourhood tokens rank LOWER; not dropped.
`limit`	No	Maximum number of items to return.
`query`	No	Text to match against venue names and descriptions; omit to list all.
`cursor`	No	Number of items to skip; pass `next_cursor` from the previous page.
`facets`	No	HARD experiential-facet filter: each token is '<facet_type>:<value>' (e.g. 'dietary:vegetarian', 'vibe:romantic'). A venue must match every facet_type given (values OR within a type, types AND across); a miss EXCLUDES it. Call facet_vocabulary for the legal types and values.
`cuisine`	No	Only return venues with this cuisine (case-insensitive exact match).
`open_on`	No	Only return venues open on this weekday (optionally at 'at'); venues with no published hours are excluded.
`open_now`	No	Only return venues open (true) or closed (false) at their own local time now; venues with no timezone or hours are excluded.
`radius_km`	No	Search radius in km around 'near' (default applied when omitted).
`price_band`	No	Only return venues in this price band, e.g. '$$' (case-insensitive).
`neighbourhood`	No	Only return venues in this neighbourhood (case-insensitive exact match).
`prefer_facets`	No	SOFT experiential-facet preference, same '<facet_type>:<value>' tokens as facets: a venue that declares them ranks higher but is NEVER dropped. Call facet_vocabulary for the legal types and values.
`prefer_cuisine`	No	Soft preference: venues of these cuisines rank higher; non-matches are NOT dropped.
`accepts_reservations`	No	Filter by whether the venue takes reservations (has a live booking tool or a booking link); omit for both.
`prefer_neighbourhood`	No	Soft preference: venues in these neighbourhoods rank higher; non-matches are NOT dropped.

Output Schema

TableJSON Schema

Name	Required	Description
`item`	No
`items`	No
`reason`	No
`sample`	No
`source`	No	FR-13: which approved revision an answer was read from, and how fresh. ``source`` is ``approved-content-revision:<id>`` for every read that answers from one venue, and the literal ``directory`` for the two cross-venue reads, which have no single revision to cite.
`status`	Yes
`pagination`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 23, 2026

addedInput schema / properties / near / examples
```
Added value: +[
+  "19.0413,-98.2062"
+]
```

changedInput schema / properties / query / anyOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maxLength": 256,
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedOutput schema / properties / sample

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Sample"
+}

First observedSep 10, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description explicitly distinguishes HARD filters (exclude on miss) from SOFT preferences (never drop, only rank up/down), discloses ordering behavior ('nearest first'), explains exclusion rules for missing data (venues with no coordinates, no published hours, no timezone), and states the result payload includes capabilities and mcp_endpoint. This is far beyond the readOnly/idempotent annotations and gives agents accurate behavioral expectations.

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?

The description is a single long, dense sentence, but every clause carries necessary information. It front-loads the core purpose and uses em-dashes to separate filter groups, making the structure parseable. It could be split into shorter sentences for readability, but given 18 parameters and the need to convey hard/soft semantics, the density is justified.

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 an 18-parameter search tool with an output schema present, the description covers all cross-cutting behavioral semantics: hard vs soft filters, ordering, exclusions based on missing data, result content, and references to vocabulary tools. With the output schema handling return structure, nothing an agent needs to call this correctly is missing.

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

Parameters4/5

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

With 100% schema description coverage, the schema already documents each parameter individually. The description adds valuable global semantics by grouping filters into HARD vs SOFT, explaining the facet token format, and clarifying that prefer_* parameters only affect ranking. This meaningfully supplements the schema's per-parameter descriptions.

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 description opens with a specific verb and resource ('Search published venues by name or description') and then enumerates the full set of filter dimensions (city, cuisine, price band, neighbourhood, reservations, proximity, opening hours, experiential facets). This clearly distinguishes it from sibling tools like search_destinations, search_menus, or get_venues, and tells an agent exactly what the tool does.

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 makes the primary use case obvious: search venues with optional filters and soft preferences. It also points to list_cities and facet_vocabulary for valid values, which are the right companion tools. However, it does not explicitly state when to prefer this over get_venues or get_venue (e.g., 'for a single venue by ID, use get_venue'), so there is no explicit when-not guidance.

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

All Yenta Directory 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?