Skip to main content
Glama

Creative review

creative_review
Read-onlyIdempotent

Reviews the evidence of selected ads for the creative-map, creative-fatigue, creative-roadmap and market-test methods: available copy, asset IDs, configured goal, period and limits. Fatigue, winning status, product promises and sample thresholds appear only where the data shows them. focus=copy_test proposes one text-order test that reuses observed wording and keeps every other variable. focus=market_transfer keeps the source asset and copy and uses only the destination the person named. A source ad is a control candidate, not a validated winner. responseMode=answer returns a report; evidence returns the underlying data. Produces no asset and prepares no campaign.

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_review"
  }
}

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

A3.6/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description goes further with meaningful constraints: 'Produces no asset and prepares no campaign' and 'A source ad is a control candidate, not a validated winner' set expectations about output limits and interpretive caution. It also notes that fatigue/winning status/thresholds only appear when the data supports them, which prevents over-reading results.

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

Conciseness3/5

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

The text is dense and semantically load-bearing, but it arrives as an undifferentiated block mixing purpose, output-mode rules, method-specific behavior, and caveats. It is front-loaded with purpose, yet sentences like the list of attributes that 'appear only where the data shows them' require re-reading.

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 usefully distinguishes the report ('answer') from the underlying data ('evidence') and states what the tool will not produce. For a nested-input, read-only review tool with a 75% documented schema, the remaining gaps (pagination behavior, result shape) are minor.

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 75%, so most parameters are already documented structurally. The description adds real meaning only for the focus modes (copy_test, market_transfer) and for responseMode, whose enum has no inline schema description; limit, offset, and accountIds gain nothing beyond the schema. The added value is genuine but concentrated in two parameters.

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+resource ('Reviews the evidence of selected ads') and enumerates the methods it serves (creative-map, creative-fatigue, creative-roadmap, market-test) plus what is inspected (copy, asset IDs, goal, period, limits). It does not explicitly contrast with close siblings such as creative_insights or creative_market_evidence, so the boundary between them is left to 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?

Conditional behavior is spelled out for focus=copy_test and focus=market_transfer, and responseMode guidance is unusually explicit about when 'evidence' is warranted versus 'answer'. However, there is no statement of when to pick this tool over the sibling review/insight tools, which is the harder selection decision for an agent.

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.