Tool Selection

GTM Tools has 60+ tools across five categories. Picking the cheapest tool that answers your question is the single biggest lever for keeping spend under control.

Decision flow

”I have a domain and want to know who works there”

1. Qualify first. Run detect_signal (free dispatch + 5/detector). If nothing fires, stop.
2. get_linkedin_company_url (2 credits): confirm the company has a LinkedIn page.
3. Pick the employee tool that matches your need:
   • search_linkedin_company_employees (5 credits): SERP-only, returns name + headline + LinkedIn URL. Best for discovery and high-volume passes.
   • list_linkedin_company_employees (30 credits): verified via Sales Navigator, returns location/current_company/etc. Best when you need richer fields. Always pass boolean title filters; the limit parameter doesn’t reduce cost.

”I have a name and a company”

1. get_linkedin_profile_url (5 credits): resolves to a profile URL.
2. get_linkedin_profile (2 credits): only if you need the full structured profile.

Don’t call list_linkedin_company_employees to find one specific named person; that’s 30 credits vs. 5.

”I have a name and want their social accounts”

1. get_social_profiles (5 credits): returns LinkedIn, X, Instagram and TikTok handles in one call.

Use get_linkedin_profile_url instead if LinkedIn is all you need and you know the domain: same 5 credits, but it’s cached, so a repeat lookup costs nothing and returns instantly. Reach for get_social_profiles when you need the platforms LinkedIn tools can’t reach, or when you don’t have a company domain to resolve against.

Pass company, domain, location or keywords whenever you have them. Context is corroborated against each candidate’s snippet before it is accepted, so it filters rather than merely re-ranks. On a common name with no context, expect the highest-ranking namesake rather than your target.

”I need this person’s email”

1. get_email (5 credits): pass name + domain.
2. Check status. An ok is verified; a not_found carries a reason (catch_all means the domain accepts everything, so nothing can be confirmed).

”I want to know what tech a company uses”

1. signal_technologies_identified (5 credits) with the specific techs array.
2. Don’t run detect_signal if this is the only signal you care about, since the dispatch will run other detectors too.

”I want to read posts from a company”

list_linkedin_company_employees_posts is by far the most expensive LinkedIn tool. Only use it when you actually need the fanout; otherwise scope to specific profile URLs with list_user_posts.

Free tools to lean on

Server selection

Only point your MCP client at the servers you actually need. Adding them all is fine, but it grows your agent’s tool list and risks the model picking the wrong one.

Filter early, hydrate late

A common mistake is fetching full profiles for everyone in a list, then filtering in code:

1
// Bad: 2 credits × 25 = 50 credits
2
const profiles = await Promise.all(
3
  employeeUrls.map(url => call("socials", "get_linkedin_profile", { profile_url: url }))
4
);
5
const decisionMakers = profiles.filter(p => /VP|Director|Head/.test(p.title));

Use list_linkedin_company_employees with title_filters instead: one 30-credit call gets you the filtered list directly:

1
// Good: 30 credits
2
const { results } = await call("socials", "list_linkedin_company_employees", {
3
  domain: "gymshark.com",
4
  title_filters: "(VP OR Director OR Head) AND Sales NOT intern",
5
  limit: 25,
6
});

Then hydrate only the candidates you actually want to message.

Next steps