Metadata MCP Connector

Pause Experiment Keyword

pause_experiment_keyword

Destructive

Pause a specific keyword running in an experiment.

            PURPOSE:
            Pause a keyword that is currently active in an experiment. This stops the keyword
            from being used in the experiment without removing it entirely.

            SCOPE - THIS TOOL ACTS ON ONE KEYWORD, NOT ON THE EXPERIMENT:
            It pauses a SINGLE keyword INSIDE an experiment. The experiment itself keeps
            running with its other keywords. To pause or restart a WHOLE experiment,
            use manage_experiment instead.

            WHEN TO USE:
            - Pause an underperforming keyword in an experiment
            - Temporarily stop a keyword from running in a specific experiment
            - Manage keyword performance within experiments

            PREREQUISITE:
            Use list_experiment_keywords first to find the keywordExternalId and wizExperimentId
            for the keyword you want to pause. Both come from that tool's results:
            keywordExternalId identifies the keyword on the ad channel, and wizExperimentId
            is the experiment's ID (the same ID search_experiments returns as experimentId).

            WORKFLOW:
            1. Search for the keyword: list_experiment_keywords(keywordOrExperimentName="my keyword")
            2. Note the keywordExternalId and wizExperimentId from the results
            3. Pause it: pause_experiment_keyword(keywordExternalId=12345, wizExperimentId=678)
            4. (Optional) Verify later: list_experiment_keywords(keywordOrExperimentName="my keyword")
               to check the status has changed

            PARAMETERS:
            - keywordExternalId: Required. The external ID of the keyword to pause (from list_experiment_keywords).
            - wizExperimentId: Required. The experiment ID where the keyword is running (from list_experiment_keywords).

            WARNING: This action changes the state of the keyword in the experiment.
            The keyword will stop running in the specified experiment.

            WARNING: ASYNC FLOW: Pausing a keyword is an asynchronous operation. The status change
            may not be immediately reflected. Use list_experiment_keywords after some time
            to verify the keyword status has been updated.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`wizExperimentId`	Yes	The experiment ID where the keyword is running.
`keywordExternalId`	Yes	The external ID of the keyword to pause.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds significant behavioral context: it warns that the action changes state, is asynchronous, and that the status may not update immediately, advising verification via list_experiment_keywords. It also explains that the keyword is paused but not removed. This goes well beyond what annotations provide and gives the agent a clear expectation of side effects and timing.

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, SCOPE, WHEN TO USE, PREREQUISITE, WORKFLOW, PARAMETERS, WARNING). It is longer than strictly necessary for a two-parameter tool, but every section adds operational value, especially the async warning and workflow. The front-loading of purpose and scope is effective, and the warnings are appropriately placed. It earns a 4 rather than a 5 due to slight redundancy (e.g., the PARAMETERS section largely repeats the schema) but remains efficient.

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?

For a tool with only two parameters and no output schema, the description covers everything an agent needs: how to obtain the IDs, the exact workflow, the asynchronous nature, and how to verify success. It even addresses the relationship to sibling tools (manage_experiment, restart_experiment_keyword). The description is fully self-contained and leaves no critical operational gap.

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

Parameters4/5

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

The schema already documents both parameters with descriptions (100% coverage), so the baseline is 3. The description adds value by explaining that both IDs come from list_experiment_keywords and clarifying the mapping: keywordExternalId identifies the keyword on the ad channel and wizExperimentId is the experiment's ID (same as experimentId from search_experiments). This provenance information is not in the schema and helps the agent source the values correctly, justifying a 4.

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 opens with a specific verb and resource ('Pause a specific keyword running in an experiment') and immediately distinguishes its scope from manage_experiment, which pauses a whole experiment. It clearly states it acts on one keyword inside an experiment, not the experiment itself, and names the sibling restart_experiment_keyword implicitly. This leaves no ambiguity about what the tool does.

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?

The description includes a dedicated WHEN TO USE section with concrete scenarios (pause underperforming keyword, temporarily stop a keyword) and explicitly says to use manage_experiment for whole-experiment pauses. It also provides a PREREQUISITE and WORKFLOW that tell the agent exactly when and how to call it, including which sibling (list_experiment_keywords) to use first and how to verify afterward. No inference is left to the agent.

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?