Skip to main content
Glama

Review Apple Ads

ads_review

Read the founder's Apple Ads for the last days (campaigns, keywords, search terms: taps, installs, spend, cost per install) and propose changes with the numbers behind each: exact keywords for search terms that install, negatives for terms that spend with no installs, bid moves toward the target, pauses, more budget where a campaign is capped at a good cost. With the app's vendor number saved it also reads what came after the install (trials, offers and subscriptions started, from App Store Connect): afterInstall gives the share of downloads that start one and the estimated cost per start, the target can be a cost per trial (targetCostPerStart), and when not one started after enough installs no bid goes up, no budget grows and each campaign that still spends gets a pause proposal; a campaign paused that way gets a resume proposal once starts come. With starts, a campaign's countries whose downloads start nothing while the app's rate expects some get a proposal to stop showing there. Apple never ties a start to a keyword, so keywords and search terms are judged by installs. structure: where the account differs from Apple's campaign structure (brand, category and competitor on exact match with Search Match off, one discovery campaign with the others' exact keywords as negatives, new users only, iPad apart), for the founder to change in Apple Ads. Proposals wait for the founder's approval on the App Store page of the results app; nothing changes in Apple Ads before. Growth. Free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ads_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoDefault 30
targetCpiNoThe founder's target cost per install, in the account's currency; default the account's average
targetCostPerStartNoThe founder's target cost per trial (or per subscription when the app has no trial), in the account's currency; turned into a cost per install with the share of downloads that start one. targetCpi wins when both are given

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / targetCostPerStart
      Added value: +{
      +  "description": "The founder's target cost per trial (or per subscription when the app has no trial), in the account's currency; turned into a cost per install with the share of downloads that start one. targetCpi wins when both are given",
      +  "exclusiveMinimum": 0,
      +  "type": "number"
      +}
  2. Added

TDQS

A3.5/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the agent knows this writes something but not where. The description supplies that missing context: proposals are staged for approval and nothing changes in Apple Ads before then. It also discloses substantive rules, such as no bid going up, no budget growing and pause proposals appearing when no starts follow enough installs, plus the constraint that starts are never tied to a keyword.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the body is a dense run-on stream of colon- and comma-separated clauses, including the literal label 'structure:' embedded mid-sentence, which reads as an artifact rather than an organizing device. The trailing 'Growth. Free.' carries no actionable information. The length is defensible for the policy it encodes, but the structure is hard to parse.

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?

With no output schema, the description carries the burden of explaining what comes back, and it does so in domain terms: per-country proposals, afterInstall share and cost per start, resume proposals, and the structural gap list. What remains thin is the response shape itself and how a proposal is keyed for approval. For a tool of this complexity with three optional parameters, it is close to sufficient.

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 days, targetCpi and targetCostPerStart already carry their own descriptions including the rule that targetCpi wins when both are given. The description adds contextual meaning by explaining that targetCostPerStart is converted to a cost per install using the share of downloads that start one. Baseline 3 is appropriate because the schema does the heavy lifting.

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 opening clause states a specific verb and resource set: reads Apple Ads campaigns, keywords and search terms with taps, installs, spend and cost per install, then proposes changes. That is more concrete than a sibling name alone would convey. It does not explicitly differentiate itself from ads_propose or ads_setup, so the agent must infer that ads_review is the read-plus-propose pass.

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?

Usage is implied rather than stated: run it to review the account and get proposals, and proposals wait for the founder's approval on the results page. There is no explicit when-to-use versus ads_propose, ads_setup or analytics, nor a stated prerequisite such as the vendor number being needed for the after-install section. The conditional 'with the app's vendor number saved it also reads...' is the closest thing to a usage condition.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources