Local SEO Data

Official

Overview Schema Source Related Servers Discussions(1)Admin

google_reviews

Read-only

Retrieve actual Google review text, ratings, dates, authors, and owner replies for sentiment analysis or reply auditing. Returns totals and averages for each business.

Instructions

Use when reading actual review text and owner replies for sentiment analysis or reply auditing. Returns text, rating, date, author_name, owner_reply for each review plus total_reviews and average_rating. For multi-location brands pass place_id (from business_profile) — name+location lookups can silently return empty. Costs 1 credit per 10 reviews. May take 10-30 seconds.

Input Schema

Name	Required	Description
`sort`	No	Sort order. Default: newest
`limit`	No	Number of reviews (1-100). Default: 10
`language`	No	Review language as ISO 639-1 code or name (e.g. "fr", "French"). Default "en" machine-translates non-English reviews — pass the market's language to get original review text.
`location`	Yes	City and state
`place_id`	No	Google Place ID for exact match (recommended for multi-location brands)
`business_name`	Yes	Business name

Output Schema

Name	Required	Description	Default
`reviews`	Yes
`total_reviews`	Yes
`average_rating`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.1.0Oct 22, 2026

addedInput schema / properties / language

Added value: +{
+  "description": "Review language as ISO 639-1 code or name (e.g. \"fr\", \"French\"). Default \"en\" machine-translates non-English reviews — pass the market's language to get original review text.",
+  "type": "string"
+}

addedInput schema / properties / place_id

Added value: +{
+  "description": "Google Place ID for exact match (recommended for multi-location brands)",
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "average_rating": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "reviews": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "author_name": {
+            "type": "string"
+          },
+          "author_url": {
+            "type": "string"
+          },
+          "date": {
+            "type": "string"
+          },
+          "owner_reply": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "owner_reply_date": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "rating": {
+            "type": "number"
+          },
+          "text": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "text",
+          "rating",
+          "date",
+          "author_name",
+          "author_url",
+          "owner_reply",
+          "owner_reply_date"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total_reviews": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "reviews",
+    "total_reviews",
+    "average_rating"
+  ],
+  "type": "object"
+}

First observedv0.1.0May 11, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond the readOnly/openWorld annotations: cost (1 credit per 10 reviews), expected latency (10-30s), a silent-failure mode for ambiguous lookups, and the fact that the default language machine-translates. That is exactly the context an agent needs to plan a call and interpret an empty result.

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?

Front-loads the trigger, then return shape, then the parameter caveat, then cost and latency. Every sentence carries a distinct constraint; nothing is restated from the schema without a reason.

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 read-only lookup with a full schema and output schema, the remaining unknowns are the ones that actually cause bad calls — cost, latency, ambiguous-match emptiness, translation behaviour — and all four are covered.

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 coverage is 100%, so the description's job is only to add meaning. It usefully elevates place_id to a recommended override and flags that the language default translates rather than returns originals — real added value — but sort, limit and business_name get no treatment. Marginally above the baseline.

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?

States a specific verb and resource — reading review text and owner replies — plus the intended analysis use (sentiment, reply auditing) and the exact fields returned. It never names its closest siblings (multi_platform_reviews, review_velocity), so an agent must infer that this one is Google-only and text-level rather than aggregate or velocity.

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?

Opens with an explicit "Use when..." trigger and gives a concrete operational rule: pass place_id for multi-location brands because name+location can silently return empty. It stops short of naming when to prefer a different review tool, so there is no true exclusion guidance.

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