Skip to main content
Glama

Create a campaign

create_campaign

Use this when the user wants a new outreach campaign. Creates a draft that will write to the people on up to 10 people lists. A manual campaign (the default) gets one empty step per channel to be written; an ai-generated campaign has its steps written from prompt in the background, so read the campaign until that writing has finished; a templateId copies a saved template's steps. Nothing is sent until the campaign is launched. Messages go out from 9:00 to 17:00 in the campaign's time zone, Monday to Friday unless set otherwise, and open and click tracking are off unless turned on. Free. Calling again creates a second campaign.

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": {
      "name": "<name>",
      "listIds": "<listIds>"
    },
    "name": "create_campaign"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe campaign's name.
typeNo`manual` (the default): you write every step. `ai-generated`: the steps are written from `prompt` in the background.
promptNo`ai-generated` only: what you offer and to whom, up to 5,000 characters. The steps are written from it.
ctaLinkNoThe link steps insert where they write `{CTA Link}`: an http or https URL, or null or empty for none.
listIdsYes1 to 10 of your people lists. Their people are enrolled once each, in the order the lists are given, when the campaign launches.
channelsNoOne empty step is made for each channel, in order: `email`, `linkedin_connection` (an invitation), `linkedin_message` (to a connection) or `inmail`. `["email"]` when left out. At most one `linkedin_connection`, before every `linkedin_message`. Not with `templateId`.
timezoneNoThe IANA time zone the sending days and hours (9:00 to 17:00) are read in, such as `Europe/Lisbon`: a region, not an abbreviation such as EST. UTC when a campaign is created without one.
emailDaysNoThe days messages may go out, by English name with a capital first letter. Monday to Friday when left out.
isDynamicNoEnrolls people added to the campaign's lists after launch, as they arrive. False when left out.
startDateNoWhen sending may start, as an ISO 8601 date-time. Now when left out.
templateIdNoA campaign template whose steps are copied into the campaign; they decide its channels, so send no `channels` with it.
excludeListsNoUp to 10 people lists whose people are never enrolled, matched by person, email address or LinkedIn profile. An id that is not one of your lists excludes nobody.
knowledgeHubIdNo`ai-generated` only: the knowledge hub the steps draw on. Your default hub when left out.
writingStyleIdNo`ai-generated` only: the writing style the steps follow. Your default style when left out.
dailyEmailLimitNoThe most emails the campaign sends a day, 1 to 10,000, or null for no limit.
excludeContactedNoSkips people your campaigns already wrote to: `none` (the default) skips nobody, `ever` skips everyone written to, and `last_1_month` to `last_1_year` skip those written to in that time.
addUnsubscribeLinkNoEnds every email with a one-click unsubscribe link. True when left out.
excludeCompanyListsNoUp to 20 company or people lists: nobody who works at one of their companies is enrolled. A list the organization does not have answers `422` `exclude_company_lists_invalid`.
clickTrackingEnabledAtNoTurns click tracking on from this ISO 8601 date-time, or off with null. Off when left out. A step that waits for a click needs it on.
excludeEngagedContactsNoSkips people who replied to one of your campaigns. False when left out.
dailyLinkedinMessageLimitNoThe most LinkedIn messages and InMails the campaign sends a day, 1 to 10,000, or null for no limit.
openRateTrackingEnabledAtNoTurns open tracking on from this ISO 8601 date-time, or off with null. Off when left out.
dailyLinkedinConnectionLimitNoThe most LinkedIn invitations the campaign sends a day, 1 to 10,000, or null for no limit.
sendOnlyToValidatedEmailsEnabledAtNoFrom this ISO 8601 date-time, enrolls only people whose email address checked `valid`; null also enrolls catch-all and unchecked addresses.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false and idempotentHint=false, but the description adds substantial context: nothing is sent until launch, ai-generated mode writes steps asynchronously so the campaign must be polled, default sending window is 9:00–17:00 Mon–Fri in the campaign time zone, tracking is off unless enabled, and it is free. That is real behavior beyond the annotation flags.

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?

Front-loaded with the usage trigger, then mode semantics, then lifecycle and defaults. Sentences are dense but each carries distinct information, and the closing 'Free. Calling again creates a second campaign.' is compact handling of cost and non-idempotency.

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 24-parameter creation tool with no output schema, it covers lifecycle (draft vs launch), asynchronous AI writing, sending-window and tracking defaults, and mode exclusivity. It does not say what identifier the call returns or what permissions/plan limits apply, but the gaps are minor against a fully described schema.

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; the description still adds cross-parameter constraints the schema states only locally: channels must be omitted with templateId, the default channel list is ["email"], and manual campaigns get one empty step per channel while AI campaigns derive steps from prompt. It does not restate every parameter default, but the mode interactions are the highest-value semantics.

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?

States a specific verb and resource ('Creates a draft' campaign) and immediately distinguishes three creation modes: manual (default, one empty step per channel), ai-generated (steps written from prompt in the background), and templateId (copies a saved template's steps). An agent can tell exactly what will be 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 Guidelines4/5

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

Opens with explicit when-to-use ('Use this when the user wants a new outreach campaign') and warns that calling again creates a second campaign, which steers the agent away from blind retries. It does not name sibling alternatives such as duplicate_campaign or save_campaign_as_template, so the routing is implied rather than explicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources