Skip to main content
Glama

campaignstack

by io.campaignstack

campaignstack_enrich_lead_contact_info

Resolve a lead's work email through the CampaignStack Contact Finder (the default) or a connected enrichment provider (provider-parameterized: bettercontact, apollo, instantly or clay). Single lead. Writes the email onto the lead following the enrichment write-back rules (fill-empty; a guessed email never overwrites an existing one; upgrade-to-verified allowed) and charges CampaignStack enrichment credits only on success. bettercontact is the CampaignStack Contact Finder: no integration needed, it charges 10 credits per email found and 50 per phone found (revealPhone: true), nothing when not found; credits are reserved at request time and refunded for anything not found. It is asynchronous: the tool returns status pending with a requestId and creditsReserved, then poll campaignstack_get_contact_finder_request (or campaignstack_list_contact_finder_requests) until the request is completed or failed; a lead that already has the requested data returns enriched with alreadyPresent: true. instantly runs SuperSearch enrichment (billed in the tenant's Instantly credits; pick types via instantlyEnrichments - work_email and/or profile, where profile fills headline/summary/title/company from the lead's LinkedIn URL) and may return status pending when still running (re-run in a minute). clay runs the routine named by clayRoutineId (required with provider clay; Clay's API cannot list routines, the user copies the id from their Clay workspace) and may also return status pending. Returns status: enriched (email and/or profileWritten), pending (bettercontact, instantly, clay), not_found (no provider match, free), or error (e.g. INTEGRATION_NOT_CONNECTED, INTEGRATION_KEY_INVALID, INTEGRATION_RATE_LIMITED, CREDITS_EXHAUSTED, WORKSPACE_LOCKED). Masked/placeholder emails are never returned as data. apollo, instantly and clay require a connected integration for the provider (campaignstack_connect_apollo / campaignstack_connect_instantly first); bettercontact never does.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
leadIdYes
providerNoEnrichment provider (default: bettercontact). bettercontact is the CampaignStack Contact Finder: no integration to connect, 10 CampaignStack credits per email found and 50 per phone found, nothing when not found; it returns status pending with a requestId to poll via campaignstack_get_contact_finder_request. apollo uses the workspace's own connected Apollo key (no CampaignStack credits). instantly runs SuperSearch enrichment billed in the tenant's Instantly credits and may return status pending (re-run in a minute). clay runs the routine given in clayRoutineId (billed in the tenant's Clay credits) and may also return status pending.
leadSourceNoLead source table (default: global). Private leads are workspace-scoped CSV imports.
revealPhoneNobettercontact only: also look up the lead's phone number. 50 CampaignStack credits per phone found (reserved at request time, refunded when not found). Ignored for other providers.
workspaceIdNoWorkspace ID (required for user keys; workspace keys are bound)
clayRoutineIdNoClay only, required with provider clay: the Clay routine id to run. Clay's API cannot list routines; the user copies the id from their Clay workspace.
instantlyEnrichmentsNoInstantly only (default ["work_email"]): "work_email" finds the work email (1.5 Instantly credits); "profile" fills headline/summary/title/company details from the lead's LinkedIn URL (0.5 credits; requires the lead to have a LinkedIn URL).

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedInput schema / properties / workspaceId / description
      Previous value: -"Workspace ID (defaults to the bound workspace)"New value: +"Workspace ID (required for user keys; workspace keys are bound)"
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

The description goes well beyond the annotations by disclosing asynchronous behavior (status pending with requestId), credit reservation/refund mechanics, write-back rules (fill-empty, never overwrite, upgrade-to-verified), the masked-email policy, and specific error codes. This is high-value behavioral context for a mutation tool.

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 and dense but every sentence carries decision-relevant information for a complex provider-parameterized, asynchronous, credit-billed operation. It is front-loaded with the core action and write-back rules. A structured bullet layout would improve scannability, but there is no real waste.

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 and seven parameters including provider-specific variants, the description covers the full lifecycle: request, pending, success, not-found, and error states, plus polling routes and integration prerequisites. An agent has enough context to invoke the tool correctly and handle asynchronous results.

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?

Although schema coverage is 86%, the description adds substantial meaning beyond the schema: provider-specific credit costs, defaults for provider and instantlyEnrichments, the fact that revealPhone is ignored for non-bettercontact providers, clayRoutineId's requirement and sourcing, and provider-specific async behavior. It transforms parameter names into actionable decisions.

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: 'Resolve a lead's work email' via named providers, and clarifies it operates on a single lead. It also distinguishes itself from related tools by stating the write-back behavior and credit implications, so an agent can differentiate it from enrichment and lead-update siblings.

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?

The description gives clear provider-selection guidance: bettercontact needs no integration, while apollo, instantly, and clay require connected integrations. It also names the polling tools to use after a pending result. It does not explicitly contrast itself with nearby alternatives like update_lead_contact_info or priority_enrich, but the intended use context is strongly implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All campaignstack toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation3/5

The set is enormous and generally well-differentiated through detailed cross-referenced descriptions, but several clusters blur together: archive/delete/remove have inconsistent permanence semantics (delete_campaign vs remove_signal_watch vs archive_campaign), create_connection_watch_agent explicitly overlaps with set_account_watcher, and the parallel draft-checkup and playbook-proposal flows (run_draft_checkup/get_draft_checkup/accept_draft_checkup vs propose_playbook_change/get_playbook_proposal/decide_playbook_proposal) present near-identical decision pipelines.

Naming Consistency4/5

Nearly every tool follows the campaignstack_<verb>_<noun> convention with disciplined get/list pairing and consistent verb choices (create/update/delete/pause/resume). Minor deviations like campaignstack_priority_enrich (adverb+verb) and campaignstack_whoami break the strict verb_noun pattern but are isolated and do not hinder navigation.

Tool Count1/5

223 tools is an extreme surface for any MCP server. Even though each tool maps to a distinct API operation and the underlying platform is broad, the scale far exceeds the 50+ threshold for an extreme mismatch and will overwhelm agents with selection overhead.

Completeness5/5

The surface is exhaustive for the LinkedIn outreach domain: full campaign/workflow/lead-list lifecycles, ICP and persona management, content scheduling and approvals, inbox and messaging, enrichment and integrations, signal watches and exclusions, review queues, playbook versioning, workspace admin, billing, and notifications. Minor gaps like a missing delete_lead or delete_company are explained by shared-data semantics, so no critical dead ends remain.

Resources