Skip to main content
Glama

Metadata MCP Connector

Get Performance Metrics

performance_metrics
Read-only

Granular performance metrics for ads, audiences, creatives, offers, target groups, keywords. IMPORTANT: Always specify endpoint parameter. Always use ISO 8601 for dates.

USE FOR: Best performing ads/audiences/creatives/offers/target groups, ingredient comparisons, ad type analysis (IMAGE, VIDEO, CAROUSEL), lead gen forms vs landing pages, pipeline by ingredient, creative previews, keyword performance. NOT FOR: Account-level stats, experiment-level analysis without ingredient focus.

ENDPOINT LOGIC:

  • 'target group' → customAudience/group

  • 'audience' → customAudience

  • 'offer'/'lead gen'/'landing page' → offer

  • 'creative' → creative

  • 'keyword' → keywords

  • 'ad'/'ads' or default → ads

AD TYPES: IMAGE, VIDEO, CAROUSEL, DOCUMENT, CONVO, SPOTLIGHT, SEARCH, MESSAGE

  • The adFormat field on each response row identifies the ad type.

METRICS: spend, impressions, clicks, leads, mqls | opens, sends, actionClicks, costPerOpen, costPerSend (CONVO/MESSAGE ads) | cpl, cpc, cpm, ctr, conversionRate, formConversionRate, mqlRate | totalOpps, totalTriggered, oppsAmount, triggeredAmount | cpMql, cpOppInfluenced, cpOppTriggered | channel, goal, adFormat, audienceSize, statusLabel | previewUrl

CONVO/MESSAGE AD CAVEAT: when adFormat is CONVO or MESSAGE (LinkedIn message ads), success is measured by opens, sends, and actionClicks (and costPerOpen / costPerSend), NOT clicks/ctr/cpc. Do not rank these ads by CTR or dismiss them when clicks=0. Use sort='actionClicks,desc' or sort='opens,desc' for conversational performance ranking.

RULES: Field 'id' corresponds to endpoint queried. Exclude $0 CPL experiments from calculations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idsNoSet of IDs to filter by
pageNoPage number to retrieve (0-based indexing)
sizeNoNumber of results per page. Default 100; raise it freely (up to 10000) for comprehensive full-dataset analysis.
sortNoSorting criteria (e.g., 'spent,desc', 'cpl,asc', 'experimentId,spent,desc')
tagsNoSet of tag IDs to filter by
goalsNoFilter by campaign goals
adNameNoFilter by specific ad name
maxCplNoMaximum cost per lead threshold
minCplNoMinimum cost per lead threshold
endDateNoendDate in ISO 8601 format (YYYY-MM-DDThh:mm:ssZ), e.g., `startDate=2025-06-12T14:30:00.123Z`).
keywordNoFilter by specific keyword
channelsNoFilter by marketing channels
endpointNoSpecific endpoint to query. If not specified, will be auto-determined from query context. Use 'customAudience/group' for target groups.
maxLeadsNoMaximum number of leads threshold
maxSpendNoMaximum spend threshold
minLeadsNoMinimum number of leads threshold
minSpendNoMinimum spend threshold
adFormatsNoFilter by ad format types. Applied to ads endpoint automatically.
offerNameNoFilter by specific offer name
startDateNostartDate in ISO 8601 format (YYYY-MM-DDThh:mm:ssZ), e.g., `startDate=2025-06-12T14:30:00.123Z`).
offerTypesNoFilter by offer types. LG=Lead Gen forms, LP=Landing Pages
oppsEndDateNoEnd date for opportunities data in ISO 8601 format
campaignNameNoFilter by specific campaign name
creativeNameNoFilter by specific creative name
visibilitiesNoFilter by visibility status. The platform knows only VISIBLE (live) and ARCHIVED; there is no HIDDEN value and sending one is rejected with a 400.
accountTagIdsNoSet of account tag IDs to filter by
audienceTypesNoFilter by audience types
experimentIdsNoSet of experiment IDs to filter by
oppsStartDateNoStart date for opportunities data in ISO 8601 format
showWithSpendNoShow only experiments/ingredients with spend data
customFieldIdsNoCustom field IDs to include
experimentListNoExperiment list filter
experimentNameNoFilter by specific experiment name
budgetGroupNameNoFilter by specific budget group name
maxAudienceSizeNoMaximum audience size threshold
minAudienceSizeNoMinimum audience size threshold
skipCustomFieldsNoSkip custom fields in response
customAudienceNameNoFilter by specific custom audience name
usedInActiveExperimentsNoFilter for ingredients used in active experiments only
launchedExperimentStatusesNoFilter Performance Metrics by experiment launch statuses only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already mark this as read-only and non-destructive; the description adds substantial behavioral context: endpoint auto-logic, ad-type caveats, response row fields, metric semantics, and the exclusion of $0 CPL experiments. It also warns against ranking CONVO/MESSAGE ads by CTR and clarifies when to use actionClicks/opens instead, behavior not inferable from annotations alone.

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

Conciseness5/5

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

Although lengthy, the description is densely structured with bolded section headers (IMPORTANT, USE FOR, NOT FOR, ENDPOINT LOGIC, AD TYPES, METRICS, RULES), front-loading the most critical instructions first. Each section earns its place by covering a distinct operational concern for a 40-parameter tool.

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?

With no output schema, the description compensates by listing all relevant metric fields, endpoint choices, response row elements, and ad-type caveats. It also states rules like excluding $0 CPL experiments and the endpoint/id correspondence, covering everything an agent needs to call this tool correctly.

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 coverage is 100%, so the baseline is 3. The description adds meaningful parameter-level guidance beyond schema: it explains the endpoint parameter mapping, recommends raising the size parameter for full-dataset analysis, and gives sorting advice for conversational ads. It does not explain every filter parameter, but the schema already documents those clearly.

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 states a specific verb and resource: it retrieves granular performance metrics for ads, audiences, creatives, offers, target groups, and keywords. It also distinguishes itself from account-level and experiment-level analytics via the explicit USE FOR/NOT FOR sections, making it clear this is the ingredient-focused metrics tool among siblings.

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 explicit USE FOR and NOT FOR lists, giving clear context for when to invoke this tool versus account-level or experiment-level tools. It also provides endpoint mapping logic and a CONVO/MESSAGE ad caveat with specific sort recommendations, so an agent knows exactly when and how to use it.

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.

Resources