Google Play MCP

reply_to_review

Post or replace a public developer reply to a Google Play review, with a dry-run preview to check the review, existing reply and length before publishing.

Instructions

Post (or replace) the PUBLIC developer reply to a review. Visible to everyone on Google Play. Max ~350 characters; HTML is stripped. Gated by PLAY_MCP_ALLOW_REVIEW_REPLIES. Set dryRun:true to see the review, any existing reply and length check without posting.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "packageName": "<packageName>",
      "reviewId": "<reviewId>",
      "replyText": "<replyText>"
    },
    "name": "reply_to_review"
  }
}

Input Schema

Name	Required	Description
`dryRun`	No	Preview without posting (default false)
`reviewId`	Yes
`replyText`	Yes	Reply text (max ~350 chars)
`packageName`	Yes	Application id (package name), e.g. com.example.app

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the behavioral load and does so well: it discloses public visibility, HTML stripping, the ~350 character ceiling, an environment-variable feature gate, and replace-on-repeat semantics. It stops short of error behavior (e.g. what happens if the review does not exist or the caller lacks permission) and does not describe the response payload.

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?

Four short sentences, front-loaded with the action and visibility, then constraints, then the safety escape hatch. No filler or redundant restatement; every clause carries distinct information.

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?

For a mutation tool with no annotations and no output schema, this covers the essentials an agent needs: what is mutated, who sees it, input constraints, feature gating, and a safe preview mode. The remaining gap is response/error behavior, which is a minor omission given the tool's simplicity.

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 description coverage is 75%, so most parameters are already documented. The description adds genuine meaning only for dryRun, explaining what the preview returns (the review, any existing reply, and a length check); packageName and reviewId get no additional semantics, and the character limit is simply repeated from the schema.

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?

States a specific verb and resource ("Post (or replace) the PUBLIC developer reply to a review") and immediately scopes the visibility ("Visible to everyone on Google Play"). It also distinguishes itself from the read-side sibling get_review by making clear this is the write path, so an agent can pick correctly without opening schemas.

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?

Explains the operating conditions well: it is gated by PLAY_MCP_ALLOW_REVIEW_REPLIES, and dryRun:true gives a non-destructive preview. It does not explicitly name get_review as the tool to read reviews without replying, so alternative selection is only implied rather than stated.

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

Deploy Server