Skip to main content
Glama
This connector has been deprecated

Duplicate listing. The official PumpGTM connector is https://glama.ai/mcp/connectors/com.pumpgtm/mcp (same server, https://mcp.pumpgtm.com/mcp).

Check a proposed campaign

check_campaign
Read-onlyIdempotent

Check a campaign you proposed (find_people targeting plus save_sequence_draft steps) before anything is saved: whether its targeting can be searched, how many profiles match its filters (a count only; audience=sample adds up to 3 example people, only when the customer asks to see some) and any message rule problems. Uses no Energy and saves nothing. Up to 3 size checks a day count (zero-match and failed ones do not); audience.say is the line to tell the customer. Quote any proposed proof, numeric claim, observation about teams or free offer back for approval unless the customer supplied it. Save approved campaigns with find_people confirmed=false and save_sequence_draft, and attach their sequences. Show the campaign, audience size and closest case study before the one get_workspace setup.nextStep ask; request a card only to find people and LinkedIn only to send. After an uncertain add, read the review and report only confirmed additions. Never finds people for outreach or contacts anyone. Only a workspace owner or admin's connection may use it. Returns targeting, audience (with say), audienceChecksToday, samplePeople and messages.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "campaign": "<campaign>"
    },
    "name": "check_campaign"
  }
}

Input Schema

NameRequiredDescriptionDefault
campaignYesThe proposed campaign: targeting, steps, executionModel and whether to include sample people.
workspaceIdNoA teammate's workspace you may manage: an active workspace ID from list_team_workspaces. Omit for your own workspace. Supply on every call for a teammate.

Output Schema

NameRequiredDescriptionDefault
savedYesAlways false.
presentNoHow to present the check to the customer.
audienceYesHow many profiles match the filters; profiles, not buyers.
messagesYesWhether the messages pass PumpGTM's rules.
targetingYesWhether the targeting can be searched and size-checked.
energyUsedYesAlways 0: checks use no Energy.
samplePeopleYesUp to 3 example people when audience=sample, otherwise empty.
audienceChecksTodayNoToday's size check allowance; null when it could not be read or the targeting was not size-checkable.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds genuinely non-obvious behavior: cost ('Uses no Energy and saves nothing'), a quota ('Up to 3 size checks a day count (zero-match and failed ones do not)'), an auth constraint ('Only a workspace owner or admin's connection may use it'), and a note that audienceChecksToday is returned. None of that is derivable from the structured fields, and nothing contradicts them.

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?

The purpose and quota are correctly front-loaded in the first two sentences, but the body drifts into workflow policy that is not about this tool: card requests, LinkedIn-only-to-send, quoting proof for approval, re-reading a review after an uncertain add. That material belongs to sibling tools and dilutes the signal for a two-parameter read-only check.

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?

For a read-only validator with a full output schema, the description covers everything an agent needs to call it correctly and interpret it: cost, daily quota and its exclusions, auth requirement, sample-mode policy, the meaning of audience.say, and a short statement of return fields. Nothing material is left ambiguous.

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 description coverage is 100%, so the nested targeting, steps, audience, executionModel and workspaceId are all fully documented in the schema; baseline is therefore 3. The description only adds a light gloss on audience=sample ('up to 3 example people') and never mentions workspaceId, so it does not meaningfully extend parameter meaning beyond what the schema already states.

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 opening sentence names a specific verb and object — check a proposed campaign composed of find_people targeting plus save_sequence_draft steps — and enumerates exactly what is validated (searchability, match count, message rule problems). That scope is distinguishable from find_people (which actually finds people) and save_sequence_draft (which actually saves), so an agent can route correctly without opening the schema.

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?

It states the timing constraint explicitly ('before anything is saved'), the mode-selection rule ('audience=sample ... only when the customer asks to see some'), and the follow-on path ('Save approved campaigns with find_people confirmed=false and save_sequence_draft'). It also names exclusions — 'Never finds people for outreach or contacts anyone' — so the when-not is covered, not just the when.

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