Skip to main content
Glama

Creative insights

creative_insights
Read-onlyIdempotent

Groups ads by their actual image or video asset, across ads and accounts. Returns winners, fatigue, repeated usage, performance, video hook and hold rates, and missing angle, offer, product, persona or creator metadata, as the basis for creative variants and hook comparisons.

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": {
      "input": "<input>"
    },
    "name": "creative_insights"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes
accountIdsNoOptional account selection; can only narrow this workspace's access.
userStatementNoRequired for launch_brief: the user's request or answer for this launch, in their own words. Otherwise optional: the user's request for this call, treated as an unverified user statement, never permission or verified platform evidence.
idempotencyKeyNoRequired for mutations. Reuse the same key only when retrying the exact same call; a completed outcome is applied once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / userStatement / description
      Previous value: -"Required for launch_brief: the latest verbatim user request or free-text answer. Otherwise optional user-provided context, treated as an unverified user statement, never permission or verified platform evidence."New value: +"Required for launch_brief: the user's request or answer for this launch, in their own words. Otherwise optional: the user's request for this call, treated as an unverified user statement, never permission or verified platform evidence."
  2. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description adds genuine behavioral value by disclosing the grouping unit (the actual image/video asset, not the ad record) and the analytic surface returned, including fatigue and hook/hold rates. It says nothing about result volume, the meaning of 'winners' or 'fatigue' thresholds, or the effect of the undocumented `input.limit` cap, which leaves the agent guessing at output shape.

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?

Two sentences with no filler; the grouping mechanism is front-loaded before the returns list, which is the right ordering. The second sentence is a long comma-separated enumeration that reads as a dump of every metric, which slightly dilutes scanability but each item is substantive.

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?

There is no output schema, so the description must carry return semantics, and it does list the metric families an agent will receive. However, for a cross-account aggregation tool with a nested parameter object and a hard 30-row cap, it omits result granularity, ordering, pagination/truncation behavior, and how many accounts the grouping spans. Adequate to select the tool, thin for interpreting what comes back.

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 75%, so the baseline is 3 and the description does not raise it: no parameter is mentioned by name, and the nested `input` object's `limit` and `accountIds` have no descriptions anywhere. The phrase 'across ads and accounts' only loosely gestures at the accountIds scoping parameter. The schema does the heavy lifting, and the undocumented nested limit (max 30) is a real gap the description could have closed.

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 opens with a specific verb and resource: grouping ads by their actual image or video asset, across ads and accounts, and then names the concrete outputs (winners, fatigue, repeated usage, hook/hold rates, missing metadata). An agent can tell this is an asset-level creative analysis tool rather than an account- or campaign-level one. It stops short of naming the nearest siblings (creative_review, creative_market_evidence, campaign_media), so differentiation still requires inference.

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 only implied through the trailing clause 'as the basis for creative variants and hook comparisons,' which suggests the downstream task but never states when to choose this over creative_review or performance_diagnose. There are no exclusions, prerequisites, or account-scope constraints stated. An agent gets a directional hint but no routing rule.

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.