Apogee: Bulk Ad Launcher for Meta, TikTok & Snapchat

TikTok / Snapchat winners and losers

get_platform_top_performers

Read-onlyIdempotent

Rank TikTok or Snapchat ads by a metric: what to scale, what to cut. TikTok or Snapchat: the best and the worst ads (or campaigns / ad sets: level) by a metric over a date range, among those that spent: "what is working", "what should I scale or cut". Money in the ad account's currency, days in its time zone; one platform at a time (never add TikTok and Snapchat up). For Meta: get_top_performers.

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": {
      "platform": "<platform>",
      "ad_account_id": "<ad_account_id>",
      "metric": "<metric>"
    },
    "name": "get_platform_top_performers"
  }
}

Input Schema

Name	Required	Description
`level`	No	Default ad
`limit`	No	How many best and worst, default 10
`since`	No	YYYY-MM-DD, with until (both included), instead of date_preset
`until`	No	YYYY-MM-DD, with since
`metric`	Yes	What ranks them: roas, cpa, ctr, spend, purchases, revenue, cpc, cpm, clicks or impressions (cpa, cpc, cpm: the lowest is the best)
`adset_id`	No	Only this ad group / ad squad's ads
`platform`	Yes	tiktok or snapchat (Meta has its own reads and actions)
`min_spend`	No	Only those that spent at least this much (account currency); those that spent nothing are always left out
`campaign_id`	No	Only this campaign's
`date_preset`	No	Default last_7d (the 7 days before today, today left out), in the ad account's time zone
`ad_account_id`	Yes	The ad account, from list_ad_accounts with the same platform: a TikTok advertiser id (digits), a Snapchat ad account id (a UUID)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive and open-world, so the bar is lower; the description still adds real context the annotations cannot: money is in the ad account's currency, days follow its time zone, and zero-spend entities are excluded from results. It stops short of describing ordering/pagination or the shape of the returned pair of lists.

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 verb and the payoff, and every clause carries information. There is mild redundancy — "TikTok or Snapchat" is restated twice and the quoted use cases repeat the scale/cut framing — which keeps it off a 5.

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 an 11-parameter tool with no output schema, the description supplies the account-currency/time-zone contract, the platform isolation rule, the spend filter, and the sibling handoff. The remaining gap is that the return shape (best vs worst lists, how limit splits between them) is left to the schema and annotations.

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 baseline is 3; the description largely restates what the schema documents (metric ranking direction, level, spend threshold, date range). The added value is limited to the account-currency and time-zone framing and the implicit best-and-worst split.

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?

Opens with a specific verb and resource ("Rank TikTok or Snapchat ads by a metric") plus the business intent ("what to scale, what to cut"), and immediately distinguishes itself from the Meta sibling by name. An agent can tell this apart from get_top_performers and get_platform_performance without opening a schema.

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?

Explicit routing is given for the alternative ("For Meta: get_top_performers") and an exclusion is stated plainly ("one platform at a time (never add TikTok and Snapchat up)"). It also scopes the population to entities that spent, so the agent knows the answer set before calling.

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

All Apogee: Bulk Ad Launcher for Meta, TikTok & Snapchat 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.