Skip to main content
Glama

PumpGTM

by com.pumpgtm.mcp
OverviewDiscussionsAdmin
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).

Review found people

review_people
Idempotent

Without decisions: read one review batch with its candidates and saved choices. With decisions: record the customer's good_fit and not_a_fit choices; each good_fit is added to the Play's sequence (or the top-level sequenceId) at once, so when the customer says add these people, that call is the enrollment and needs no further confirmation. People the customer did not pick stay for later; finish=true is optional and only closes the review. When the Play has no sequence, pass the workspace's active sequence as sequenceId, asking which one only when there are several. For a Play made with find_people play, pass its playId to read the people it found; good_fit adds them to the Play's sequence at once (sequenceId attaches one first) and not_a_fit skips them. Sends nothing in this call. Open world: people queued into a live sequence are later contacted by its paced steps.

Input Schema

NameRequiredDescriptionDefault
finishNo
playIdNoInstead of batchId, for a Play made with find_people play.
batchIdNo
decisionsNo
requestIdNoRequired with decisions.
sequenceIdNo
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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / playId
      Added value: +{
+  "description": "Instead of batchId, for a Play made with find_people play.",
+  "format": "uuid",
+  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "batchId"
-]
  2. Changed1 schema field changed
    • changedInput schema / properties / workspaceId / description
      Previous value: -"Team owner only: an active workspace ID from list_team_workspaces. Omit for your own workspace. Supply on every call for a teammate."New value: +"A 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."
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Beyond annotations, it discloses the key side effect that good_fit enrolls people immediately with no further confirmation, that unpicked people remain for later, that finish only closes the review, and that outreach is paced later. This is valuable behavioral context, though the description is somewhat tangled and does not mention permissions or rate limits.

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 dual-mode structure is front-loaded, but the description is long and repetitive, especially around immediate enrollment. It is appropriately sized for a complex tool but could be tightened significantly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex seven-parameter tool with no output schema, it covers the main behavioral and workflow context: read vs write, sequence enrollment, finish semantics, and open-world pacing. It is missing explicit return-value detail and some parameter documentation, but is largely complete.

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?

With schema coverage at 43%, the description meaningfully explains decisions, playId, batchId, sequenceId, and finish. But it omits requestId, workspaceId, and the feedback fields, and does not fully compensate for the schema's coverage gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states two clear modes: reading a review batch with candidates and saved choices, and recording good_fit/not_a_fit decisions with sequence enrollment. It distinguishes this enrollment behavior from a separate add step, but does not explicitly name sibling tools like add_to_sequence or review_x_play_candidates.

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?

It clearly describes when to use each mode: omit decisions to read, supply decisions to record choices. It also explains sequence handling and when to ask which sequence to use. However, it does not explicitly state when not to use this tool or name alternatives beyond find_people.

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

All PumpGTM toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources