Skip to main content
Glama
closermethod

SMB Sales Intelligence MCP

get_discovery_script

Qualify prospects with a tailored discovery script. Choose a tone to match your relationship and ask the right questions before pitching.

Instructions

Get a discovery script to qualify prospects before pitching. Always ask questions first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toneYesprofessional=email/linkedin, warm=existing relationship, ultra_short=DM, cold_outbound=first contact, inbound_lead=they reached out

Implementation Reference

  • Input schema for get_discovery_script: requires a 'tone' parameter with enum values (professional, warm, ultra_short, cold_outbound, inbound_lead).
    inputSchema: {
      type: "object",
      properties: {
        tone: {
          type: "string",
          enum: ["professional", "warm", "ultra_short", "cold_outbound", "inbound_lead"],
          description: "professional=email/linkedin, warm=existing relationship, ultra_short=DM, cold_outbound=first contact, inbound_lead=they reached out"
        }
      },
      required: ["tone"]
    }
  • Handler for get_discovery_script tool call: extracts tone arg, looks up DISCOVERY_SCRIPTS, returns discovery script with pushback handlers.
    case "get_discovery_script": {
      const tone = args?.tone as string;
      const script = DISCOVERY_SCRIPTS[tone as keyof typeof DISCOVERY_SCRIPTS];
      return {
        content: [{
          type: "text",
          text: JSON.stringify({
            module: "Discovery System",
            rule: "NEVER pitch before qualifying. Ask questions first.",
            psychology: "When prospects invest in answering questions, they're more likely to buy.",
            script: script,
            pushback_handlers: {
              just_send_rate: "Happy to — I just need those details so I don't under or overquote.",
              need_ballpark: "Totally get it. The reason I ask: scope changes the pricing significantly.",
              send_portfolio: "Happy to share — quick context first: what's the main goal here?"
            }
          }, null, 2)
        }]
      };
    }
  • DISCOVERY_SCRIPTS constant: defines script templates for each tone variant (professional, warm, ultra_short, cold_outbound, inbound_lead).
    const DISCOVERY_SCRIPTS = {
      professional: {
        tone: "professional",
        context: "Email, LinkedIn DM, formal settings",
        template: `Great timing — quick 2 questions before I put anything together:
    
    1. What's the main outcome you're hoping to achieve with this?
    2. What's driving the timeline — is there a launch date or deadline I should know about?
    
    Once I have that, I'll send 3 options that fit your situation.`
      },
      warm: {
        tone: "warm",
        context: "Existing relationship, warm intro, second touchpoint",
        template: `Absolutely — 2 quick ones so I don't guess:
    
    1. What's the main goal here?
    2. Any deadline driving this?
    
    Then I'll send options that actually fit.`
      },
      ultra_short: {
        tone: "dm",
        context: "Instagram DM, text, informal",
        template: `Quick 2 before I quote:
    What's the goal? Any deadline?
    Then options.`
      },
      cold_outbound: {
        tone: "cold",
        context: "First cold email or LinkedIn message",
        template: `Hi [Name],
    
    Quick question: is [specific problem you solve] something that's on your radar right now, or is this a 'not right now' situation?
    
    Either answer is fine — just want to know if it's worth sending more info.`
      },
      inbound_lead: {
        tone: "inbound",
        context: "Someone reached out to you first",
        template: `Thanks for reaching out! Before I dive in, 2 quick questions:
    
    1. What prompted you to reach out now? (Helps me understand urgency)
    2. Who else would be involved in this decision?
    
    Once I know that, I'll make sure I'm showing you the right thing.`
      }
    };
  • src/main.ts:661-677 (registration)
    Tool registration: server.setRequestHandler(ListToolsRequestSchema) registering get_discovery_script as an available tool with description and input schema.
    return {
      tools: [
        {
          name: "get_discovery_script",
          description: "Get a discovery script to qualify prospects before pitching. Always ask questions first.",
          inputSchema: {
            type: "object",
            properties: {
              tone: {
                type: "string",
                enum: ["professional", "warm", "ultra_short", "cold_outbound", "inbound_lead"],
                description: "professional=email/linkedin, warm=existing relationship, ultra_short=DM, cold_outbound=first contact, inbound_lead=they reached out"
              }
            },
            required: ["tone"]
          }
        },
Behavior2/5

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

With no annotations provided, the description should disclose behavioral traits like whether the script is static or dynamic, any side effects, or required context. It only states the purpose and a general rule, which is insufficient for a tool that likely influences sales behavior.

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?

The description is exceptionally concise with two sentences that are front-loaded and waste no words, efficiently delivering the core message.

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

Completeness3/5

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

The tool is simple with one parameter and no output schema, so the description covers the minimum necessary for a basic understanding. However, it lacks details on the script's structure or behavior, which could be improved.

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?

The schema covers all parameters with detailed enum descriptions, so the description adds no extra meaning beyond the schema. The general advice 'Always ask questions first' does not relate directly to the 'tone' parameter.

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 clearly states the tool retrieves a discovery script for qualifying prospects before pitching, which differentiates it from siblings like get_call_script or get_closing_script that serve different stages.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The instruction 'Always ask questions first' provides some usage context, but there is no explicit guidance on when to use this versus alternative tools, nor any mention of prerequisites or exclusions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/closermethod/smb-sales-intelligence-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server