Skip to main content
Glama

Metadata MCP Connector

Get Converted Leads Summary (Smart Leads aggregates)

get_converted_leads_summary
Read-only

Fast aggregate summary of the account's converted leads (Smart Leads) — counts and rates only, no lead rows.

ALSO KNOWN AS: leads summary, lead totals, lead overview, MQL rate, lead-to-MQL conversion, smart leads summary.

KEYWORDS: LEAD COUNT, LEAD TOTALS, HOW MANY LEADS, LEADS SUMMARY, LEAD OVERVIEW, SMART LEADS, CONVERTED LEADS, MQL RATE, LEAD-TO-MQL, MQLS, UNIQUE LEADS, UNIQUE DOMAINS, LEAD CHANNEL MIX, LEADS BY CHANNEL, ENRICHMENT COVERAGE, SYNCED TO MARKETING AUTOMATION, LEAD QUALITY BASELINE, LEAD AUDIT BASELINE, PIPELINE FROM LEADS, TRIGGERED OPPORTUNITIES, INFLUENCED OPPORTUNITIES, LEAD SANITY CHECK

USE FOR: "How many leads do we have?", MQL rate and lead-to-MQL sanity checks, channel mix of leads (Facebook/Instagram/LinkedIn/Google Ads/display), enrichment coverage, leads synced to marketing automation, unique leads vs unique company domains, pipeline tie-back (triggered/influenced opportunities and amounts). ALWAYS call this FIRST in a lead audit to set the baseline before pulling rows with get_converted_leads.

NOT FOR: Inspecting individual leads or job-title/ICP distributions (use get_converted_leads); campaign performance metrics (use experiment_performance_stats).

RETURNED DATA: total | totalFacebook, totalInstagram, totalLinkedin, totalGoogleAds | fullyEnriched, autoEnriched, unenriched | syncedToMa | uniqueLeads, uniqueDomain | mqls, uniqueMqls, mqlRate, uniqueMqlRate | influencedOpps, triggeredOpps, influencedAmount, triggeredAmount.

RULES:

  • Accepts the same filters as get_converted_leads (no pagination/sort) — scope by campaignName/channels/startDate+endDate to summarize a slice.

  • mqlRate is a useful lead-quality indicator, but clients define MQL criteria differently and it rarely matches a true MQL — treat it as a secondary signal next to job-title/ICP fit.

  • uniqueDomain vs total shows lead concentration: many leads from few domains can mean a few companies dominate the results.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idsNoRestrict the summary to specific lead IDs.
emailNoFilter by lead email (partial match).
adNameNoFilter by the ad (library) name that captured the leads (partial match).
syncMANotrue = only leads synced to marketing automation; false = only unsynced.
tagIdsNoFilter by tag IDs on the leads' experiments.
endDateNoLeads created on/before this date. ISO 8601; date-only is accepted.
keywordNoFilter by the exact search keyword that captured the leads.
channelsNoFilter by acquisition channel(s).
jobTitleNoFilter by lead job title (partial match).
lastNameNoFilter by lead last name (partial match).
statusesNoLead statuses to include. The platform Leads tab defaults to ACTIVE. Omit to include all.
companiesNoFilter by exact company names.
countriesNoFilter by exact lead country names.
firstNameNoFilter by lead first name (partial match).
offerNameNoFilter by the offer name tied to the leads' experiments.
startDateNoLeads created on/after this date. ISO 8601; date-only is accepted.
matchTypesNoFilter by keyword match type (search channels).
modifiedByNoFilter by the platform user email who last modified the leads (partial match).
campaignNameNoFilter by campaign name (partial match).
contentTypesNoData-completeness filter: only leads that HAVE this content.
qualityTypesNoQuality-signal filter (opportunities, MQL date/score).
audienceTypesNoFilter by audience type of the leads' experiments (e.g. FIRMOGRAPHIC_INCLUDE, CONTACT_LIST, BUYER_INTENT, NATIVE_LINKEDIN).
isAutoUpdatedNotrue = only auto-enriched leads.
businessEmailsNoFilter by exact business email addresses (OR within the list).
experimentNameNoFilter by experiment name (partial match).
isFullyEnrichedNotrue = only fully enriched leads; false = only not fully enriched.
isManuallyUpdateNotrue = only manually enriched/edited leads (platform parameter name is 'isManuallyUpdate').
customAudienceNameNoFilter by targeted audience name (partial match).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already signal read-only and non-destructive behavior, but the description adds meaningful context: it returns only aggregates, not lead rows; it lists the exact returned fields; it explains no pagination/sort; and it cautions that mqlRate is not a true MQL. It also adds interpretive guidance on uniqueDomain vs total concentration.

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 long, mostly due to the alias and keyword blocks, but it is well-structured and front-loaded with the core purpose. The USE FOR, NOT FOR, RETURNED DATA, and RULES sections each add distinct value, so the length is justified even if somewhat exhaustive.

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?

Given the large 28-parameter schema and no output schema, the description compensates well: it lists the returned aggregate fields, describes typical use cases, excludes unrelated use cases, and gives important interpretation caveats. An agent has enough context to call the tool correctly and interpret the response.

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 description doesn't need to restate filter parameters. It still adds value by noting that it 'accepts the same filters as get_converted_leads (no pagination/sort)' and by naming the most useful scoping filters (campaignName/channels/startDate+endDate) for summarizing a slice.

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: 'Fast aggregate summary of the account's converted leads (Smart Leads) — counts and rates only, no lead rows.' This clearly distinguishes the tool from lead-row-retrieval tools like get_converted_leads, so an agent can identify what it does and what it does not return.

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 section lists concrete questions the tool answers, NOT FOR names the correct alternatives, and the description explicitly says to 'ALWAYS call this FIRST in a lead audit to set the baseline before pulling rows with get_converted_leads.' This is explicit when/when-not guidance with named alternatives.

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