app-publish-mcp

google_create_release

Create or update a Google Play release with an explicit version-code set, defining track, status, release notes, and rollout settings while Play retains fallback releases.

Instructions

Create or update one release with an explicit version-code set. Google Play retains fallback releases; send only the desired change.

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>",
      "editId": "<editId>",
      "track": "<track>",
      "versionCodes": "<versionCodes>"
    },
    "name": "google_create_release"
  }
}

Input Schema

Name	Required	Description	Default
`track`	Yes	Target track ID, including custom or form-factor tracks returned by google_list_tracks
`editId`	Yes	Edit ID
`status`	No		completed
`packageName`	Yes	Android package name
`releaseName`	No	Release name/label
`releaseNotes`	No	Release notes per language
`userFraction`	No	Staged rollout fraction (exclusive range 0-1; not supported for internal)
`versionCodes`	Yes	Complete version-code set for this release
`countryTargeting`	No	Country targeting for an inProgress production rollout
`inAppUpdatePriority`	No	In-app update priority from 0 (lowest) to 5 (highest); cannot be changed after rollout

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv0.7.0Oct 25, 2026

addedInput schema / properties / countryTargeting

Added value: +{
+  "additionalProperties": false,
+  "description": "Country targeting for an inProgress production rollout",
+  "properties": {
+    "countries": {
+      "default": [],
+      "items": {
+        "pattern": "^[A-Z]{2}$",
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "includeRestOfWorld": {
+      "default": false,
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

addedInput schema / properties / inAppUpdatePriority

Added value: +{
+  "description": "In-app update priority from 0 (lowest) to 5 (highest); cannot be changed after rollout",
+  "maximum": 5,
+  "minimum": 0,
+  "type": "integer"
+}

changedInput schema / properties / track / description

Previous value: -"Target track"New value: +"Target track ID, including custom or form-factor tracks returned by google_list_tracks"

removedInput schema / properties / track / enum

Removed value: -[
-  "internal",
-  "alpha",
-  "beta",
-  "production"
-]

addedInput schema / properties / track / minLength
```
Added value: +1
```

changedInput schema / properties / userFraction / description

Previous value: -"Staged rollout fraction (0.0-1.0, only for production)"New value: +"Staged rollout fraction (exclusive range 0-1; not supported for internal)"

addedInput schema / properties / userFraction / exclusiveMaximum
```
Added value: +1
```
addedInput schema / properties / userFraction / exclusiveMinimum
```
Added value: +0
```

changedInput schema / properties / versionCodes / description

Previous value: -"Version codes to include"New value: +"Complete version-code set for this release"

addedInput schema / properties / versionCodes / items / pattern
```
Added value: +"^[1-9]\\d*$"
```
addedInput schema / properties / versionCodes / minItems
```
Added value: +1
```

changedInput schema / required

Previous value: -[
-  "packageName",
-  "editId",
-  "track"
-]New value: +[
+  "packageName",
+  "editId",
+  "track",
+  "versionCodes"
+]

First observedv0.3.1Mar 19, 2026

TDQS

B3.3/5.0

Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose two non-obvious traits: this is an upsert ('create or update'), and Google Play retains fallback releases so callers need only send the desired change. It omits the edit lifecycle (must be inside an active edit, must commit), permission/auth needs, and idempotency behavior, leaving meaningful gaps for a mutation tool.

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?

Two tight sentences with the core action and the key semantic constraint front-loaded. Nothing is redundant and every clause adds information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter mutation with nested objects, no annotations, and no output schema, the description is thin on workflow context. The rich schema compensates for field-level detail, but the edit/commit lifecycle and relationship to promote/halt siblings 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?

Schema coverage is 90%, so parameters are already well documented. The description's 'explicit version-code set' merely echoes the schema's 'Complete version-code set for this release' and adds no format, ordering, or interaction detail beyond structured data; baseline 3 is appropriate.

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 (create/update) and resource (one release) plus the defining constraint 'explicit version-code set,' which is enough to distinguish it from status-listing or halt tools. It does not, however, name or differentiate against close siblings like google_promote_release or google_halt_release, which also act on releases.

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?

No explicit when-to-use/when-not guidance. The phrase 'send only the desired change' hints at how to call it, but nothing tells the agent when to prefer google_promote_release or google_halt_release, nor that an active edit and subsequent commit are required.

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

Deploy Server