Skip to main content
Glama

Metadata MCP Connector

Get Account-Level Statistics

account_level_stats
Read-only

Account-level statistics and channel breakdown for a timeframe.

USE FOR: General account stats by period, channel breakdown, high-level metrics (ROI, spending, leads, opportunities), custom date ranges. NOT FOR: Campaign-level info (use experiment_performance_stats), specific experiments (use get_experiments).

CHANNELS: FACEBOOK, LINKEDIN, GOOGLE ADS, ALL

TIMEFRAME LOGIC:

  • 'quarter'/'Q1-Q4' → timeframe='QUARTER'

  • 'week'/'weekly' → timeframe='WEEK'

  • ≤3 months → timeframe='MONTH'

  • 3 months → timeframe='QUARTER'

  • Default: timeframe='MONTH'

CUSTOM DATE RANGE: Provide ONLY startDate + endDate (NO timeframe). Format: ISO 8601 (YYYY-MM-DDTHH:mm:ss.sssZ)

NO DELIVERY: a period with no delivery comes back with empty totals and an empty channelBreakDown (the platform sends null for both); read that as zeros for every channel, not as missing data.

METRICS: impressions, clicks, spent, leads, mqls | opens, sends, actionClicks (CONVO/MESSAGE ads) | triggeredOpps, triggeredOppsAmount, influencedOpps, influencedOppsAmount | triggeredClosedWonOpps, triggeredClosedWonOppsAmount | roiInfluencedOpp, roiTriggeredOpp | cpc, cpl, cpm, ctr, conversionRate | costPerOpen, costPerSend (CONVO/MESSAGE ads) | customFields array

CONVO/MESSAGE AD CAVEAT: opens, sends, actionClicks (and their per-cost derivatives) are the success metrics for CONVO and MESSAGE (LinkedIn message) ad types. clicks/ctr/cpc are typically 0 for these ads — do not treat that as "no performance". If account-level data shows high spend with 0 clicks, drill into experiment_performance_stats or get_ad_details to confirm ad type before drawing conclusions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endDateNoEnd date for custom date range in ISO 8601 format (YYYY-MM-DDTHH:mm:ss.sssZ). Must be used together with startDate. Do NOT provide timeframe when using this. Example: 2025-09-30T00:00:00.000Z
startDateNoStart date for custom date range in ISO 8601 format (YYYY-MM-DDTHH:mm:ss.sssZ). Must be used together with endDate. Do NOT provide timeframe when using this. Example: 2025-07-01T00:00:00.000Z
timeframeNoTimeframe for data aggregation. MONTH=monthly breakdown, QUARTER=quarterly breakdown, WEEK=weekly breakdown, YEAR=yearly breakdown. DO NOT use this parameter when providing startDate and endDate.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A5/5.0
Behavior5/5

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

Beyond the readOnlyHint and destructiveHint annotations, the description reveals non-obvious behavior: a period with no delivery returns null for totals and channelBreakDown and should be interpreted as zeros, not missing data. The CONVO/MESSAGE ad caveat also prevents a serious misinterpretation where zero clicks looks like no performance.

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?

The description is long but every section earns its place: purpose, usage boundaries, channel values, timeframe logic, custom date caveats, no-delivery behavior, and metrics. Section headers make it scannable, and the most decision-critical guidance is front-loaded.

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?

There is no output schema, so the description compensates by enumerating the available metrics and describing the channelBreakDown shape, including the null-handling behavior. Combined with channel values, timeframe rules, and the CONVO/MESSAGE caveat, an agent has everything needed to call this tool correctly.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds substantial semantic value beyond the schema: it maps plain-language inputs like 'quarter', 'Q1-Q4', 'week', and 'weekly' to enum values, defines month-vs-quarter thresholds, states the default, and clarifies that custom date ranges must omit timeframe. This significantly improves correct invocation.

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 statement: 'Account-level statistics and channel breakdown for a timeframe,' and reinforces it with USE FOR examples. It also distinguishes itself from related siblings by explicitly saying it is NOT for campaign-level info or specific experiments, naming experiment_performance_stats and get_experiments as alternatives.

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 USE FOR / NOT FOR sections give explicit guidance on when to use this tool versus alternatives. It also provides concrete timeframe selection rules and custom-date-range constraints, so an agent knows exactly when to pass timeframe versus startDate/endDate.

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