Metadata MCP Connector

Get Keyword Performance Statistics from Experiments

experiments_keywords_stats

Read-only

Keyword performance data from active experiments with date range filtering.

Input Schema

Name	Required	Description	Default
`page`	No	Page number for pagination (0-based). Example: page=0 for the first page, page=1 for the next one.
`size`	No	Results per page from 1 to 100; default 50. Use successive zero-based page values and response pagination metadata for more results.
`sort`	No	Sorting criteria as field,direction (direction 'asc' or 'desc'). Sortable fields: keyword, wizExperimentName, adGroup, matchType, status, spend, impressions, clicks, ctr, cpc, cpm, cpl, leads, mqls, cpMQL, conversions, allConversions, interactions, qualityScoreHist, totalOpps, oppsAmount, totalTriggered, triggeredAmount. Default: 'spend,desc'.	spend,desc
`endDate`	Yes	End date in ISO 8601 format (YYYY-MM-DDTHH:mm:ss.sssZ). Example: '2025-12-31T23:59:59.999Z'
`startDate`	Yes	Start date in ISO 8601 format (YYYY-MM-DDTHH:mm:ss.sssZ). Example: '2025-01-01T00:00:00.000Z'
`keywordOrExperimentName`	No	Optional substring filter matched against the keyword text and the experiment name. Omit it to get every keyword in the window.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 25, 2026

changedInput schema / properties / size / description

Previous value: -"Number of keywords per page. Default: 50; raise it (up to 10000) to pull the full keyword set in one call."New value: +"Results per page from 1 to 100; default 50. Use successive zero-based page values and response pagination metadata for more results."

changedInput schema / properties / size / maximum
```
Previous value: -10000New value: +100
```

First observedSep 16, 2026

TDQS

C2.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds the 'active experiments' scoping constraint, which is useful, but says nothing about pagination behavior, result volume, or what happens when no active experiment matches.

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?

One short sentence with no filler, but it is under-specified rather than concise: the entire description is a single noun phrase, so there is no front-loaded instruction and no supporting detail to earn its brevity.

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

Completeness2/5

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

With six parameters, no output schema, and a metrics-oriented return payload, the description should explain what metrics come back (spend, clicks, CTR, conversions, etc.) and how pagination metadata works. Neither is covered, leaving the agent to guess at the response shape from sortable field names.

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 100%, with page, size, sort, dates and the keywordOrExperimentName filter all documented in the schema. The description only restates the date-range filter, so it adds nothing beyond the schema; baseline 3 applies.

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?

Names the resource precisely: keyword-level performance data scoped to active experiments, with date-range filtering. This distinguishes it from experiment-level siblings like experiment_performance_stats and from list_experiment_keywords, though the differentiation is implicit rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no mention of alternatives such as experiment_performance_stats (experiment-level rollups) or list_experiment_keywords (structural listing). The agent must infer selection from the name alone.

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?