App Pain API

Mine app pain points

mine_app_pain_points

Read-onlyIdempotent

THE core tool: fetch recent reviews of any iOS/Android app, keep the negative ones, and cluster them into ranked pain points (title, sharePercent, severity 1-5, verbatim evidence quotes). Ideal for competitive research and product discovery. Cached 7 days (instant on repeat); a COLD server-side analysis takes 30-120s. If the result has "mode":"agent", it contains prepared negative reviews and "instructions" — do the clustering yourself and present it to the user.

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": {
      "appId": "<appId>"
    },
    "name": "mine_app_pain_points"
  }
}

Input Schema

Name	Required	Description
`appId`	Yes	App Store or Google Play URL, iOS / Mac App Store numeric id (e.g. 324684580) or Android package (e.g. com.spotify.music) — get ids from search_apps
`model`	No	premium refinement model (paid keys only). Omit for the free default.
`store`	No	optional — inferred from appId (numeric id / App Store URL → ios, package / Play URL → android); iOS and Mac App Store share the same URL shape, so pass "macos" explicitly for Mac apps
`analyze`	No	who clusters on a cold run: "server" = our model; "agent" = you get the prepared negative reviews + instructions and cluster them with your own model; "auto" (default) = server, switching to agent when the server-side allowance is used up
`country`	No	ISO country code, default "us"
`reviews`	No	reviews to analyze, default 300 (other values round up to these tiers; Apple rate limiting can occasionally cap depth below the target)
`maxRating`	No	ratings <= this count as negative, default 3

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 6, 2026

changedInput schema / properties / reviews / description

Previous value: -"reviews to analyze, default 300 (other values round up to these tiers; iOS/macOS depth is ~50 due to Apple edge limits)"New value: +"reviews to analyze, default 300 (other values round up to these tiers; Apple rate limiting can occasionally cap depth below the target)"

Changed4 schema fields changedNov 6, 2026

changedInput schema / properties / appId / description

Previous value: -"App Store or Google Play URL, iOS numeric id (e.g. 324684580) or Android package (e.g. com.spotify.music) — get ids from search_apps"New value: +"App Store or Google Play URL, iOS / Mac App Store numeric id (e.g. 324684580) or Android package (e.g. com.spotify.music) — get ids from search_apps"

changedInput schema / properties / reviews / description

Previous value: -"reviews to analyze, default 300 (other values round up to these tiers; iOS depth is ~50 due to Apple edge limits)"New value: +"reviews to analyze, default 300 (other values round up to these tiers; iOS/macOS depth is ~50 due to Apple edge limits)"

changedInput schema / properties / store / description

Previous value: -"optional — inferred from appId (numeric id / App Store URL → ios, package / Play URL → android)"New value: +"optional — inferred from appId (numeric id / App Store URL → ios, package / Play URL → android); iOS and Mac App Store share the same URL shape, so pass \"macos\" explicitly for Mac apps"

changedInput schema / properties / store / enum

Previous value: -[
-  "ios",
-  "android"
-]New value: +[
+  "ios",
+  "macos",
+  "android"
+]

First observedOct 23, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations, it discloses critical behavior: seven-day caching, 30-120 second cold analysis, and the fallback where a returned "mode":"agent" result requires the agent to cluster the supplied negative reviews itself. Those operational details materially affect how an agent should call and handle the 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?

The description is dense but front-loaded: it states the core purpose, then the output shape, then usage context, then caching/timing, then the agent-mode fallback. Each sentence carries operational value for a tool with multiple analysis modes and latency behavior.

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?

With no output schema, the description compensates by naming the return fields (title, sharePercent, severity, evidence quotes) and explaining the agent-mode response. It also covers caching, timing, and fallback behavior, leaving no major gap for calling the tool correctly.

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 100%, so the schema already carries the meaning of appId, store, analyze, country, reviews, maxRating, and model. The description adds operational context around analysis modes and caching but does not add much parameter-level semantics beyond 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?

The description uses a specific verb-and-resource chain: fetch reviews, keep the negative ones, and cluster them into ranked pain points. It clearly distinguishes this from raw review retrieval and other sibling tools by naming the exact output artifact and analytical transformation.

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?

It gives clear use-case context, saying the tool is ideal for competitive research and product discovery, and explains the cold-run and agent-clustering paths. It does not explicitly state when to use this over siblings like get_app_reviews or get_pain_trend, so it lacks full alternative routing.

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

All App Pain API tools Inspect

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.