Metadata MCP Connector

Search Experiments

search_experiments

Read-only

Search for experiments by name, status, and budget group with flexible filtering.

            KEYWORDS: experiment, search, find, ad, test, status, active, paused, performance, campaign

            WHEN TO USE:
            - User wants to "find experiment X"
            - User asks to "show experiments for campaign Y"
            - User requests to "search for experiments matching Z"
            - User wants to "see all experiments with name containing A"
            - User asks "what experiments are in campaign B?"
            - User asks "what is the ID of experiment C?"
            - User wants to "find experiments in budget group X"
            - User asks to "search experiments in specific budget groups"
            - User wants to "show all active experiments"
            - User asks "list paused experiments"
            - User wants to "find experiments with status X"

            PURPOSE:
            This tool searches across all experiments with flexible filtering options.
            You can search by name (partial, case-insensitive), filter by budget groups, and filter by status.
            All filters are optional - use any combination to narrow down results.

            SEARCH CAPABILITIES:
            - Search by experiment name: Returns experiments with matching names
            - Search by campaign name: Returns all experiments from campaigns with matching names
            - Filter by budget groups: Narrow results to specific budget group IDs
            - Filter by status: Show experiments with specific statuses (Active, Paused, etc.)
            - Partial matching: Search term doesn't need to be exact
            - Case-insensitive: "Test" matches "test", "TEST", "TeSt"

            STATUS VALUES EXPLAINED:
            - Active: Currently running and spending budget
            - WithoutSpend: Running but not currently spending budget
            - Paused: Temporarily stopped, can be restarted
            - Completed: Finished (reached end date or completion criteria)
            - Failed: Encountered an error during execution
            - Disconnected: Connection to ad channel was lost

            RETURN EXPERIMENT DATA FIELDS:
            - experimentId, experimentName, wizCampaignId, wizCampaignName
            - campaignGroup, statusLabel, dailyBudget, spent, impressions, clicks
            - startDate, endDate

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No	Page number for pagination (default: 0)
`size`	No	Number of results per page (default: 5)
`sort`	No	Sort criteria in format 'field,direction' (e.g., 'name,asc')
`search_name`	No	The experiment or campaign name to search for (partial, case-insensitive matching). Optional - omit to skip name filtering.
`budget_group_ids`	No	Optional array of budget group IDs to filter experiments. Only returns experiments that belong to these budget groups.
`launched_experiment_statuses`	No	Optional array of experiment statuses to filter by. Valid values: Active, WithoutSpend, Paused, Completed, Failed, Disconnected

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 cover read-only and non-destructive safety, so the description need not repeat that. It adds meaningful behavioral details: partial and case-insensitive matching, plain-English meanings for each status value, and a list of returned data fields. These go beyond both the annotations and the schema.

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?

Well-structured with clear section headings and bullet points, but the WHEN TO USE list is repetitive (e.g., 'find experiment X' and 'find experiments in budget group X' are nearly identical), and the KEYWORDS section is redundant with the rest. Could be trimmed by about a third without losing information.

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?

The description covers all functional aspects: filters, combination of filters, status value meanings, and returned fields, which is especially valuable since there is no output schema. It omits pagination/sorting default behavior, but those parameters are already documented in the schema, so this is only a minor 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?

Schema description coverage is 100%, so the baseline is 3. The description adds value by explaining status semantics (e.g., 'WithoutSpend – running but not spending budget'), clarifying that filters are optional and combinable, and illustrating how budget group filtering works. This enriches the minimal schema descriptions.

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 clear verb and resource: 'Search for experiments by name, status, and budget group.' It distinguishes from sibling tools like search_campaigns_by_names by explicitly targeting experimentsholistically and enumerating the exact filter dimensions.

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?

An extensive WHEN TO USE section lists concrete user phrasings ('find experiment X', 'show active experiments') that map directly to this tool. It lacks explicit when-not-to-use guidance or named alternatives, but the examples are specific enough to disambiguate from siblings.

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?