Skip to main content
Glama
JiantaoFu

App Market Intelligence MCP

google-play-reviews

Retrieve user reviews for Google Play apps to analyze feedback, track ratings, and understand customer sentiment for market research and competitor analysis.

Instructions

Get reviews for a Google Play app. Returns an array of reviews with:

  • id: Review ID string

  • userName: Reviewer's name

  • userImage: Reviewer's profile image URL

  • date: Review date (ISO string)

  • score: Rating (1-5)

  • scoreText: Rating display text

  • title: Review title

  • text: Review content

  • url: Review URL

  • version: App version reviewed

  • thumbsUp: Number of thumbs up votes

  • replyDate: Developer reply date (if any)

  • replyText: Developer reply content (if any)

  • criterias: Array of rating criteria (if any)

Note: Reviews are returned in the specified language. The total review count shown in Google Play refers to ratings, not written reviews.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appIdYesPackage name of the app (e.g., 'com.mojang.minecraftpe')
langNoLanguage code for reviews (default: en)en
countryNoCountry code (default: us)us
sortNoSort order: newest, rating, or helpfulness (default: newest)newest
numNoNumber of reviews to retrieve (default: 100). Ignored if paginate is true.
paginateNoEnable pagination with 150 reviews per page
nextPaginationTokenNoToken for fetching next page of reviews

Implementation Reference

  • The handler function that executes the tool logic: fetches Google Play app reviews using the gplay.reviews method with provided parameters, maps sort order, handles pagination, and returns a JSON-formatted response containing the reviews data and next page token.
    async ({ appId, lang, country, sort, num, paginate, nextPaginationToken }) => {
      const sortMap = {
        newest: gplay.sort.NEWEST,
        rating: gplay.sort.RATING,
        helpfulness: gplay.sort.HELPFULNESS
      };
    
      const reviews = await gplay.reviews({
        appId,
        lang,
        country,
        sort: sortMap[sort],
        num,
        paginate,
        nextPaginationToken
      });
    
      return {
        content: [{
          type: "text",
          text: JSON.stringify({
            reviews: reviews.data,
            nextPage: reviews.nextPaginationToken
          })
        }] 
      };
    }
  • Zod schema defining the input parameters for the tool, including appId (required), lang, country, sort order, number of reviews, pagination flag, and pagination token.
    {
      appId: z.string().describe("Package name of the app (e.g., 'com.mojang.minecraftpe')"),
      lang: z.string().default("en").describe("Language code for reviews (default: en)"),
      country: z.string().default("us").describe("Country code (default: us)"),
      sort: z.enum(["newest", "rating", "helpfulness"]).default("newest")
        .describe("Sort order: newest, rating, or helpfulness (default: newest)"),
      num: z.number().default(100).describe("Number of reviews to retrieve (default: 100). Ignored if paginate is true."),
      paginate: z.boolean().default(false).describe("Enable pagination with 150 reviews per page"),
      nextPaginationToken: z.string().optional().describe("Token for fetching next page of reviews")
    }, 
  • src/server.js:479-534 (registration)
    Registration of the 'google-play-reviews' tool via server.tool(), including the tool description, input schema, and inline handler function.
    server.tool("google-play-reviews", 
      "Get reviews for a Google Play app. Returns an array of reviews with:\n" +
      "- id: Review ID string\n" +
      "- userName: Reviewer's name\n" +
      "- userImage: Reviewer's profile image URL\n" +
      "- date: Review date (ISO string)\n" +
      "- score: Rating (1-5)\n" +
      "- scoreText: Rating display text\n" +
      "- title: Review title\n" +
      "- text: Review content\n" +
      "- url: Review URL\n" +
      "- version: App version reviewed\n" +
      "- thumbsUp: Number of thumbs up votes\n" +
      "- replyDate: Developer reply date (if any)\n" +
      "- replyText: Developer reply content (if any)\n" +
      "- criterias: Array of rating criteria (if any)\n" +
      "\nNote: Reviews are returned in the specified language. The total review count\n" +
      "shown in Google Play refers to ratings, not written reviews.",
      {
        appId: z.string().describe("Package name of the app (e.g., 'com.mojang.minecraftpe')"),
        lang: z.string().default("en").describe("Language code for reviews (default: en)"),
        country: z.string().default("us").describe("Country code (default: us)"),
        sort: z.enum(["newest", "rating", "helpfulness"]).default("newest")
          .describe("Sort order: newest, rating, or helpfulness (default: newest)"),
        num: z.number().default(100).describe("Number of reviews to retrieve (default: 100). Ignored if paginate is true."),
        paginate: z.boolean().default(false).describe("Enable pagination with 150 reviews per page"),
        nextPaginationToken: z.string().optional().describe("Token for fetching next page of reviews")
      }, 
      async ({ appId, lang, country, sort, num, paginate, nextPaginationToken }) => {
        const sortMap = {
          newest: gplay.sort.NEWEST,
          rating: gplay.sort.RATING,
          helpfulness: gplay.sort.HELPFULNESS
        };
    
        const reviews = await gplay.reviews({
          appId,
          lang,
          country,
          sort: sortMap[sort],
          num,
          paginate,
          nextPaginationToken
        });
    
        return {
          content: [{
            type: "text",
            text: JSON.stringify({
              reviews: reviews.data,
              nextPage: reviews.nextPaginationToken
            })
          }] 
        };
      }
    );
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context: it specifies the return format (an array of reviews with detailed fields), notes language dependency, and clarifies that total review counts differ from written reviews. However, it lacks details on error handling, rate limits, authentication needs, or pagination behavior beyond the input schema, leaving gaps for a mutation-free tool.

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 well-structured and appropriately sized. It starts with a clear purpose statement, followed by a bulleted list of return fields and a note. Each sentence adds value, such as clarifying the distinction between reviews and ratings. It could be slightly more concise by integrating the note into the initial statement, but overall it is efficient.

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?

Given the tool's complexity (7 parameters, no output schema, no annotations), the description is reasonably complete. It explains the return structure in detail, which compensates for the lack of output schema, and adds contextual notes. However, it could improve by addressing behavioral aspects like error cases or usage limits, which are missing.

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% description coverage, providing clear details for all 7 parameters. The description does not add any parameter-specific information beyond what the schema already documents. According to the rules, with high schema coverage (>80%), the baseline score is 3, as the description does not need to compensate but also does not enhance parameter understanding.

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?

The description clearly states the tool's purpose: 'Get reviews for a Google Play app.' It specifies the verb ('Get') and resource ('reviews for a Google Play app'), making it immediately understandable. However, it does not explicitly differentiate from sibling tools like 'app-store-reviews' or 'google-play-ratings,' which would be needed for a score of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It mentions that 'total review count shown in Google Play refers to ratings, not written reviews,' which hints at a distinction from ratings tools but does not explicitly name alternatives or specify use cases. No exclusions or prerequisites are mentioned.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/JiantaoFu/AppInsightMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server