Skip to main content
Glama

Creative scores and winning patterns

meta_insights_get_creatives
Read-only

Creative analysis for Meta (and TikTok) ads: a 0-100 score per ad vs its account peers (ROAS or CPA, CTR, video hook rate), top and weakest creatives, format mix, winning copy and format patterns (questions, numbers, emoji, urgency, video vs image) and refresh briefs for fatigued ads. Use for "best creatives", "which ads work", "what should our next ad look like", "creative refresh". Google ads are not scored (no ad-level metrics synced).

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": "meta_insights_get_creatives"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNo
daysNo
limitNo
actionNo
statusNo
date_toNo
page_idNo
sort_byNo
user_idNo
site_urlNo
client_idNo
date_fromNo
ad_accountNo
ig_user_idNo
user_emailNo
range_presetNo
activity_onlyNo
campaign_nameNo
property_nameNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: the scoring benchmark (0-100 relative to account peers), the metrics used (ROAS or CPA, CTR, video hook rate), and the platform coverage limitation for Google. It says nothing about pagination, how many creatives are returned, or how the refresh briefs are generated.

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 core capability, then outputs, then use cases, then the Google caveat. It is a long single sentence with stacked parentheticals, but each clause carries distinct information, so there is little true waste.

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?

Output schema exists, so return-value explanation is not required, and annotations carry the safety profile. The material gap is the 19 undocumented optional parameters: the description never explains how to target an account, set a date window, or sort results, which matters for a tool this wide.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

19 parameters with 0% schema description coverage and no enums, yet the description names none of them — not days/date_from/date_to, sort_by, status, action, ad_account, limit, or the platform-id fields. With all parameters optional it is still callable, but an agent gets no guidance on how to scope by account or date range or how to sort.

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 concrete verb and resource (creative analysis for Meta/TikTok ads) and enumerates the specific outputs: 0-100 score vs account peers, top/weakest creatives, format mix, copy patterns, refresh briefs. It also explicitly excludes Google ads, which separates it from the google_ads_* siblings.

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?

Provides concrete trigger phrases ("best creatives", "which ads work", "what should our next ad look like", "creative refresh") and one exclusion (Google ads not scored). It does not, however, route the agent away from the fatigue-focused siblings (meta_insights_get_fatigue, meta_ads_get_fatigue) despite overlapping on fatigued-ad refresh.

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.