Outbound Sales

This guide walks through a complete outbound workflow with GTM Tools. Start from a target domain, surface buying signals, find the right decision-maker, verify their email, and send a personalized invitation — all through MCP, REST, or the CLI.

The pipeline

domain → signals → company URL → employees (filtered) → profile → email → invitation

Each step is one tool call. Tokens are reserved up front and refunded if anything fails — so a failed email lookup doesn’t cost you the 5 tokens.

Step 1: Qualify the account with signals

Before spending tokens on people lookup, run detect_signal to confirm the company actually has buying intent.

$
curl -X POST https://api.gtm-tools.sh/api/v0/detect_signal \
>
  -H "Authorization: Bearer $GTM_TOOLS_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -d '{"domain": "gymshark.com", "techs": ["zendesk.com", "intercom.com"]}'

Look for the highest-confidence signals:

If no signals fire, deprioritize the account and move on. This costs 5 tokens per detector that ran and saves you 30+ tokens you’d have spent on employee search.

Step 2: Find the company on LinkedIn

$
curl -X POST https://api.gtm-tools.sh/api/v0/get_linkedin_company_url \
>
  -H "Authorization: Bearer $GTM_TOOLS_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -d '{"domain": "gymshark.com"}'

1
{ "url": "https://www.linkedin.com/company/gymshark", "domain": "gymshark.com" }

Cost: 2 tokens.

Step 3: Search for decision-makers

Use list_linkedin_company_employees with boolean title filters tailored to whichever signal fired.

$
curl -X POST https://api.gtm-tools.sh/api/v0/list_linkedin_company_employees \
>
  -H "Authorization: Bearer $GTM_TOOLS_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "domain": "gymshark.com",
>
    "title_filters": "(VP OR Director OR Head) AND (CX OR Support OR Customer Experience) NOT intern",
>
    "limit": 10,
>
    "page": 1
>
  }'

Cost: 30 tokens — this is the most expensive step in the pipeline. Don’t run it speculatively. Always qualify with signals first.

Title filter cheat-sheet

Step 4: Verify the professional email

For each candidate from step 3, call get_email.

$
curl -X POST https://api.gtm-tools.sh/api/v0/get_email \
>
  -H "Authorization: Bearer $GTM_TOOLS_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -d '{"name": "Camille Tichard", "domain": "gymshark.com"}'

1
{
2
  "email": "camille@gymshark.com",
3
  "is_catch_all": false,
4
  "domain": "gymshark.com"
5
}

Cost: 5 tokens per email. If is_catch_all is true, treat the result as a hypothesis — see Email Finding.

Step 5: Send a personalized invitation

Bind a LinkedIn session once, then send the connection request.

$
# One-time: connect a LinkedIn session
$
curl -X POST https://api.gtm-tools.sh/api/v0/connect_linkedin \
>
  -H "Authorization: Bearer $GTM_TOOLS_API_KEY"
$
$
# Send invitation (5 tokens)
$
curl -X POST https://api.gtm-tools.sh/api/v0/send_linkedin_invitation \
>
  -H "Authorization: Bearer $GTM_TOOLS_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "profile_url": "https://linkedin.com/in/camilletichard",
>
    "message": "Hi Camille — saw Gymshark recently posted three CX team lead roles. Curious how youre thinking about ticket volume — we work with brands at your scale."
>
  }'

Personalize using the signal: a CX hiring spike justifies the angle, the negative-support reviews give you the line of attack.

End-to-end script

1
const KEY = process.env.GTM_TOOLS_API_KEY!;
2
3
4
async function call<T>(tool: string, body: unknown = {}): Promise<T> {
5
  const res = await fetch(`https://api.gtm-tools.sh/api/v0/${tool}`, {
6
    method: "POST",
7
    headers: {
8
      "Authorization": `Bearer ${KEY}`,
9
      "Content-Type": "application/json",
10
    },
11
    body: JSON.stringify(body),
12
  });
13
  if (!res.ok) throw new Error(`${tool}: ${res.status} ${await res.text()}`);
14
  return res.json();
15
}
16
17
async function prospect(domain: string) {
18
  // 1. Qualify with signals
19
  const signals = await call<any>("detect_signal", {
20
    domain,
21
    techs: ["zendesk.com", "intercom.com"],
22
  });
23
  const fired = signals.signals.filter((s: any) => s.fired);
24
  if (fired.length === 0) {
25
    console.log(`[skip] ${domain} — no signals`);
26
    return;
27
  }
28
29
  // 2. Resolve company URL
30
  await call<any>("get_linkedin_company_url", { domain });
31
32
  // 3. Find decision-makers
33
  const filter = fired.some((s: any) => s.name.includes("support"))
34
    ? "(VP OR Director OR Head) AND (CX OR Support) NOT intern"
35
    : "(VP OR Director OR Head) AND Sales NOT intern";
36
37
  const { results } = await call<any>("list_linkedin_company_employees", {
38
    domain,
39
    title_filters: filter,
40
    limit: 5,
41
  });
42
43
  // 4. Verify emails for the top 3
44
  for (const r of results.slice(0, 3)) {
45
    const { email, is_catch_all } = await call<any>("get_email", {
46
      name: r.name,
47
      domain,
48
    });
49
    console.log(`${r.name} → ${email}${is_catch_all ? " (catch-all)" : ""}`);
50
  }
51
}
52
53
await prospect("gymshark.com");

Token budget

For a single qualified prospect end-to-end:

77 tokens = $0.77 per fully-researched prospect. The free 100-token starter balance covers your first prospect with room to spare.

Next steps