Skip to main content
Glama

App insights: near the top 10 and biggest moves

get_app_insights
Read-onlyIdempotent

Analyzes one app's keyword rankings by market to surface high-demand phrases ranked 11–30 and major rank climbs or falls over 7 or 30 days, helping prioritize ASO pushes.

Instructions

One app: the same measures as get_dashboard now and per market, phrases ranked 11-30 with demand (most worth a push first: demand x closeness to the top 10), and the biggest climbs and falls over the period (by search attention won or lost; change = places, not ranked counts as 251). demand is REAL popularity when demandSource is popularity, else the ESTIMATED volume. Use keywordId + country with get_term_detail. Local data.

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": {
      "projectId": "<projectId>"
    },
    "name": "get_app_insights"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoPeriod for the moves and changes (default 7).
projectIdYesProject id (from get_overview).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.3

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no explanation. The description does add real behavioral value by defining 'demand' as REAL popularity when demandSource is popularity and ESTIMATED otherwise, and by explaining the change metric (places, with unranked treated as 251) and the 'demand x closeness to top 10' ordering, but it does not cover result size, ordering guarantees, or how market data is laid out.

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?

It is a single dense sentence with the scope constraint ('One app') front-loaded, and every clause carries information. Some parenthetical asides, particularly 'not ranked counts as 251', are cryptic and slow parsing, which keeps it off a 5.

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?

With no output schema, the description carries the burden of describing returns, and it does outline the three result groups plus the metric definitions. Still, an agent cannot tell the shape of the response, whether markets are a per-country breakdown, or how many phrases or moves come back, so it is not fully complete for a data-reading tool.

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 100% with only two parameters, both documented in the schema including the 7/30 enum and the default. The description's 'over the period' echoes the days parameter without adding syntax or constraints, and the keywordId/country mention refers to a sibling tool rather than this tool's inputs, so it lands at the baseline.

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?

The description names the resource scope ('One app') and enumerates the content returned: dashboard-equivalent measures, per-market phrases ranked 11-30 with demand, and biggest climbs/falls over the period. That is specific enough to distinguish it from the multi-app get_dashboard, though 'the same measures as get_dashboard' forces the agent to resolve another tool's semantics to fully grasp the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives one clear follow-up routing hint ('Use keywordId + country with get_term_detail'), which tells the agent what to do after reading a term. However, it never explicitly states when to call this instead of get_dashboard or get_search_terms; the contrast is only implied by 'One app'.

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

Deploy Server

Other Tools