Metadata MCP Connector

List Experiment Keywords

list_experiment_keywords

Read-only

Search and browse keywords running in experiments with simplified response data.

            PURPOSE:
            Retrieve a paginated list of keywords that are currently running in experiments,
            with optional filtering by keyword or experiment name. Returns only essential fields
            for quick identification: keyword name, keywordExternalId, wizExperimentId, wizExperimentName, and status.

            WHEN TO USE:
            - Find keywords running in a specific experiment
            - Search for a keyword across all experiments
            - Look up keywordExternalId and wizExperimentId before pausing a keyword
            - Browse experiment keywords with pagination
            - Verify the status of a keyword after calling pause_experiment_keyword
              (note: pausing is an async flow, so the status may take some time to update)

            RESPONSE FORMAT:
            Returns a simplified paginated response:
            {
              "totalElements": 50,
              "totalPages": 5,
              "data": [
                {
                  "keyword": "digital marketing",
                  "keywordExternalId": 12345,
                  "wizExperimentId": 678,
                  "wizExperimentName": "Q1 Campaign Test",
                  "status": "ACTIVE",
                  "primaryStatus": "NOT_ELIGIBLE",
                  "primaryStatusReasons": ["CAMPAIGN_PAUSED", "CAMPAIGN_PENDING"]
                }
              ]
            }

            COMMON USE CASES:
            1. Search by experiment name:
               list_experiment_keywords(keywordOrExperimentName="Q1 Campaign")

            2. Search by keyword:
               list_experiment_keywords(keywordOrExperimentName="marketing")

            3. Paginate through results:
               list_experiment_keywords(keywordOrExperimentName="test", page=0, size=20)
               list_experiment_keywords(keywordOrExperimentName="test", page=1, size=20)

            PARAMETERS:
            - keywordOrExperimentName: Required. Search term to filter by keyword or experiment name.
            - page: Page number for pagination (0-based, default: 0)
            - size: Number of items per page (default: 10)

            TIP: Use this tool first to find the keywordExternalId and wizExperimentId needed
            by the pause_experiment_keyword tool.

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No	Page number for pagination (0-based). Default is 0.
`size`	No	Number of items per page. Default is 10.
`keywordOrExperimentName`	Yes	Search term to filter results by keyword name or experiment name.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds valuable behavioral context: it details the simplified response fields, pagination structure, and the async nature of status updates after pausing. This goes beyond annotations without contradicting them.

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?

The description is well-structured with clear sections (PURPOSE, WHEN TO USE, RESPONSE FORMAT, COMMON USE CASES, PARAMETERS, TIP) and front-loaded with the purpose. It is relatively long but each section earns its place with examples and operational guidance. No fluff, though it could be slightly condensed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of an output schema, the description fully compensates by providing the exact response format with example fields. It covers pagination parameters, common use cases with code examples, and even the async status update behavior. An agent has everything needed to call this tool correctly without ambiguity.

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 each parameter is already documented in the schema. The description repeats parameter details but adds value through concrete usage examples (e.g., searching by experiment name or keyword, pagination with page and size). These examples clarify semantics but do not add meaning beyond what the schema provides, hence the baseline 3.

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?

The description clearly states the tool's function: 'Search and browse keywords running in experiments with simplified response data.' It specifies the resource (experiment keywords), the action (search/browse), and the output simplification, distinguishing it from general keyword listing tools. The purpose is unambiguous and specific.

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?

The 'WHEN TO USE' section lists five concrete scenarios, including searching by experiment, looking up IDs before pausing, and verifying status after pause_experiment_keyword. It also provides a tip to use this tool before pausing. However, it does not explicitly mention when not to use it or name alternative sibling tools like list_keywords, though the context strongly implies the differentiator.

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

All Metadata MCP Connector 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.

Resources

Need Help?