Skip to main content
Glama

Yelp

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Get Reviews

get_reviews
Read-onlyIdempotent

⚠️ UPSTREAM-UNRELIABLE — Yelp Fusion's /reviews endpoint has been 404-ing on most ids since mid-2026 even for valid businesses. PREFER get_business (which sometimes inlines a snippet) or search_businesses for review-context queries. If you must call get_reviews: pass the ENCRYPTED business id (long alphanumeric, e.g. "WavvLdfdP6g8aZTtbBQHTw") returned in search_businesses results — aliases / slugs (e.g. "garaje-san-francisco") reliably 404. Returns up to 3 review snippets per business (rating, text, author, timestamp); "limit" is capped by Yelp upstream regardless of what you pass.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesYelp business id or alias (from search_businesses results).
limitNoNumber of reviews to return (default 3, max 50).
_apiKeyNoRequired — your own Yelp Fusion key. Pipeworx fronts no platform key for Yelp (Fusion plan is $229/mo, #2275 open); every call is refused with none.
sort_byNoSort order: "yelp_sort" (default) or "newest".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / _apiKey / description
      Previous value: -"Optional — your own Yelp Fusion API key for higher limits; omit to use the shared Pipeworx key."New value: +"Required — your own Yelp Fusion key. Pipeworx fronts no platform key for Yelp (Fusion plan is $229/mo, #2275 open); every call is refused with none."
  2. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "id": "WavvLdfdP6g8aZTtbBQHTw",
+    "limit": 3,
+    "sort_by": "yelp_sort"
+  },
+  {
+    "id": "WavvLdfdP6g8aZTtbBQHTw",
+    "limit": 5,
+    "sort_by": "newest"
+  }
+]
  3. First observed

TDQS

A4.9/5.0
Behavior5/5

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

The description significantly enriches the annotations by warning that Yelp's endpoint is 'UPSTREAM-UNRELIABLE' and has been 404-ing on most ids, clarifying that limit is 'capped by Yelp upstream regardless of what you pass,' and stating that calls are refused without a user-supplied API key. These behaviors are not visible from the readOnly/idempotent annotations and are critical for correct invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence carries operational weight: the reliability warning, preferred alternatives, id format, return shape, and limit cap are all essential for correct use. The warning is front-loaded so agents immediately know the risk before deep-diving into schema details.

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?

With no output schema, the description adequately explains the return content ('rating, text, author, timestamp'), the number of items returned, failure modes, the required id format, API key necessity, and upstream cap. Nothing an agent needs to decide whether to call this tool or invoke it 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?

Schema coverage is 100%, so the baseline is 3, but the description adds valuable semantic context: the id must be the encrypted business id from search_businesses, aliases reliably fail, and the limit parameter is not honored above Yelp's cap. This goes beyond the schema's generic property 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 clearly identifies the tool as fetching Yelp reviews, states what it returns ('up to 3 review snippets per business (rating, text, author, timestamp)'), and distinguishes it from siblings by positioning get_business and search_businesses as alternatives for review-context queries. The scope and resource are specific and unambiguous.

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?

It explicitly tells agents when to avoid this tool and which alternatives to prefer: 'PREFER get_business... or search_businesses for review-context queries.' It also gives precise invocation guidance, such as passing the encrypted business id from search_businesses rather than aliases, and notes the upstream limit cap.

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

All Yelp toolsInspect
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