Skip to main content
Glama
Sign In

Android Developer MCP by Nova (CIVAI)

by co.civai.nova
OverviewDiscussionsAdmin

start_rollout

Roll out a release — this IS Android's publish action for the release. Not simply reversible; always confirm with the user, especially on production. Preconditions it cannot satisfy itself: the release needs an artifact attached (attach_artifact_to_release — promote_release does NOT attach one), and the track needs at least one EXPLICITLY selected country (target_rest_of_world alone is not a selection — see update_track_countries). A bare FAILED_PRECONDITION here names nothing: open the Console's release review page (.../tracks/{track}/releases/{release}/review) and expand its errors, which is read-only and states the cause in one sentence. Production additionally requires the app to have passed review once.

Input Schema

NameRequiredDescriptionDefault
track_idYesNumeric track id (e.g. the long digits in the Play Console URL's .../tracks/<this>/..., not the human alias like "internal"). Call list_tracks first to find it.
release_idYesRelease id on this track, from create_release/get_track.
play_app_idYesNumeric Play app id from the Play Console URL (.../app/<this>/...). NOT the package name.
developer_idYesNumeric Play Console developer id (from the Play Console URL).
rollout_percentageNoPercentage of users to roll out to, 0-100. Defaults to 100 (full rollout) if omitted.
targeted_countriesNoComma-separated ISO 3166-1 alpha-2 codes, e.g. "NG,GH,KE". NOTE: on a track that has no country targeting of its own this does NOT work — tested live, Play still refuses. Use update_track_countries to set the track's countries first; this parameter only narrows a rollout on a track that is already targeted. Nothing is defaulted — ask the user.
google_account_emailYesThe signed-in Google account email that owns this Play Console developer account. Call list_accounts first and confirm with the user — do not guess.
notification_messageNoShort user-facing sentence for this action if the follow-up reply fails. Plain text only; do not mention template syntax or variable names.
target_rest_of_worldNo"true" serves every country/region Play allows; "false" serves only targeted_countries. Omitted is NOT the same as "false" — it keeps whatever the track already targets. Same caveat as targeted_countries: it cannot stand in for update_track_countries on an untargeted track.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it declares the operation not simply reversible, requires user confirmation, gates production on a prior review pass, and explains the failure mode. It does not describe the success response or what the returned rollout state looks like, which is a remaining gap given there is no output schema.

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?

Front-loaded with the destructive action and its confirmation requirement, and nearly every sentence earns its place. The FAILED_PRECONDITION sentence is dense and slightly run-on, costing some readability.

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 9-parameter, annotation-free mutation with no output schema, the description covers safety, preconditions, and error recovery well. It leaves the return/rollout-state behavior and the effect of the rollout_percentage/target_rest_of_world defaults unaddressed in prose.

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 baseline is 3, but the description adds genuine cross-parameter meaning: target_rest_of_world alone is not a valid country selection, and targeted_countries only narrows an already-targeted track. That interdependence is behavioral, not merely per-field.

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 ("Roll out a release") and immediately defines the scope: "this IS Android's publish action for the release." That framing cleanly separates it from the sibling promote_release and attach_artifact_to_release.

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?

Explicitly names when to use it (publish a prepared release), when to stop and confirm with the user (always, especially production), and the exact prerequisites plus the sibling that satisfies each (attach_artifact_to_release, update_track_countries). It even routes the agent to a read-only diagnostic path for a bare FAILED_PRECONDITION.

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

All Android Developer MCP by Nova (CIVAI) 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