Skip to main content
Glama
Sign In

AppmanAi

by com.appmanai
OverviewDiscussionsAdmin

Get app reviews

app_reviews
Read-only

Read real user reviews of an app: author, star rating, text and date, 40 per page. Use it to find out what users actually complain about or praise. On Google Play, page through in order (1, 2, 3…) while has_more is true, each page within about an hour of the previous one and with the same sort_type; skipping ahead fails with PAGE_EXPIRED (not charged), so start again from page 1. The App Store serves a single page: there is no page 2 on ios. Costs 4 credits.

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": {
      "store": "<store>",
      "country": "<country>",
      "package": "<package>"
    },
    "name": "app_reviews"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, 1 by default. Only the page after the last one read (within about an hour, same sort_type) works; Google Play only.
storeYesWhich app store: "android" (Google Play) or "ios" (App Store).
countryYesTwo-letter ISO country code, e.g. "US", "GB", "DE".
packageYesApp package / bundle id, e.g. "com.discord" (Android) or a numeric App Store id. If you only have the app name, call app_search first to resolve it.
sort_typeNoReview sort order: 0 most relevant, 1 most recent (default), 3 top rated.
star_filterNoOnly reviews with this star rating.
force_updateNoBypass the cache and refetch from the store. Slower; use sparingly.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnly/openWorld annotations: it discloses the 4-credit cost, the 40-per-page cap, the PAGE_EXPIRED failure mode (and that it isn't charged), the ~1 hour paging window requiring a consistent sort_type, and the iOS single-page limitation. That is exactly the behavioral context an agent cannot infer from structured fields.

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 purpose and per-page shape, then the operational caveats. Every sentence carries information, though the Google Play paging sentence is dense and packs several constraints into one run-on clause.

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?

Given seven parameters, no output schema, and a non-trivial pagination protocol, the description covers what an agent must know: return fields, page size, store-specific paging rules, error handling, and credit cost. Nothing essential is missing.

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 the baseline is 3; the description adds real meaning on top by explaining that `page` only advances sequentially and must keep the same `sort_type`, and by tying page behavior to the store. It still doesn't discuss `star_filter`, `country`, or `force_update` beyond what the schema says.

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 ("read real user reviews of an app") plus the exact fields returned (author, star rating, text, date) and page size. It is clearly distinguishable from siblings like app_metrics_ratings_history, which aggregate rather than return review text.

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?

Gives explicit usage motivation ("find out what users actually complain about or praise") and detailed operational rules: sequential paging on Google Play, single-page behavior on iOS. It does not name a sibling alternative (e.g. app_search for resolving package ids is only referenced in the schema), so it falls just short of a 5.

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

All AppmanAi 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