PumpGTM

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).

Track AI search questions

add_ai_search_questions

Idempotent

Track buyer questions, written as a buyer would ask ChatGPT or Google. Up to 50 tracked questions in total; questions already tracked are skipped. Questions that name the company are marked branded. Adding asks no engine and spends no Energy; run_ai_search_check does. Returns how many were added and every tracked question with its questionId. If AI search is not on for this workspace yet, this turns it on (aiSearchTurnedOn in the result says what it starts with). Only for a connection created by a current owner or admin of this workspace.

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": {
      "questions": "<questions>"
    },
    "name": "add_ai_search_questions"
  }
}

Input Schema

Name	Required	Description	Default
`questions`	Yes	Buyer questions to track, one per item, worded as a buyer would ask an AI assistant (for example "best CRM for a small agency").
`workspaceId`	No	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.

Output Schema

Name	Required	Description
`added`	Yes	How many questions were newly tracked; questions already tracked are skipped.
`questions`	Yes	Every tracked question with its questionId.
`aiSearchTurnedOn`	No	Present only when this call turned AI search on: what it now runs with. Tell the customer.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 10, 2026

changedInput schema / properties / questions / description

Previous value: -"Buyer questions as a buyer would ask an AI assistant, one line each, 3 to 400 characters."New value: +"Buyer questions to track, one per item, worded as a buyer would ask an AI assistant (for example \"best CRM for a small agency\")."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "added": {
+      "description": "How many questions were newly tracked; questions already tracked are skipped.",
+      "type": "number"
+    },
+    "aiSearchTurnedOn": {
+      "description": "Present only when this call turned AI search on: what it now runs with. Tell the customer.",
+      "type": "string"
+    },
+    "questions": {
+      "description": "Every tracked question with its questionId.",
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "branded": {
+            "description": "True when the question names the company; branded questions don't count toward topics.",
+            "type": "boolean"
+          },
+          "createdAt": {
+            "description": "When it started being tracked (ISO time).",
+            "type": "string"
+          },
+          "questionId": {
+            "description": "Pass to get_ai_search_question, run_ai_search_check or remove_ai_search_question.",
+            "type": "string"
+          },
+          "source": {
+            "description": "How it was added: suggested, manual or audit.",
+            "type": "string"
+          },
+          "text": {
+            "description": "The question as tracked.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "questionId",
+          "text",
+          "branded",
+          "source",
+          "createdAt"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "added",
+    "questions"
+  ],
+  "type": "object"
+}

AddedNov 6, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Goes well beyond the annotations: discloses that adding costs no Energy, that already-tracked questions are skipped, that company-naming questions are marked branded, and that AI search is silently enabled if off (surfaced as aiSearchTurnedOn). That side-effect disclosure is exactly the kind of mutation context the readOnly/destructive hints cannot convey.

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?

Purpose is front-loaded, then cost, dedupe, side effects, return shape, and permissions in descending order of decision value. The parentheticals are informational rather than filler, and no sentence merely restates the tool name or annotations.

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 two-parameter mutation with an output schema available, the description closes the remaining gaps an agent needs: cost model, cap, duplicate handling, implicit enablement of a feature, and authorization scope. Nothing required to call it correctly is left unstated.

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 baseline is 3, but the description adds meaning the schema does not: the buyer-voiced phrasing constraint, the 50-item ceiling, and the branded-tagging effect of naming the company in a question. It also indicates the return includes questionId per tracked question.

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?

Opens with a specific verb and resource ('Track buyer questions') and immediately qualifies the artifact as buyer-voiced queries for ChatGPT or Google, which separates it from sibling suggest_ai_search_questions and run_ai_search_check. An agent can identify what gets created 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?

Explicitly routes the agent: adding is free of engine calls and Energy, whereas run_ai_search_check is what spends them. It also states the 50-question cap, that duplicates are skipped, and the owner/admin connection prerequisite, so when-to-use and when-not-to-use are both covered.

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

All PumpGTM tools Inspect

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

Need Help?