Skip to main content
Glama

Schedule campaign

campaign_schedule
Destructive

Schedules a drafted campaign to send to its audience. This is not reversible once sending starts, and it uses one email of quota per recipient. Call campaign_preview first, tell the person the audience count and the quota it uses, and only call this after they say yes. Pass the audience count you showed them as expected_audience_count; if the list changed meaningfully the call is refused. A workspace's first campaign is held for a one-time human review instead of sending (review_pending); say so plainly and do not retry. Before send_at, campaign_cancel can still stop it. Requires API key scope: send.

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": {
      "id": "<id>",
      "send_at": "<send_at>",
      "expected_audience_count": "<expected_audience_count>",
      "confirm": "<confirm>"
    },
    "name": "campaign_schedule"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesCampaign id (a UUID), as returned by campaign_draft or campaigns_list.
confirmYesMust be true, and only after the person explicitly approved this send and its audience count.
send_atYes"now", or an ISO 8601 time with timezone such as 2026-10-05T09:00:00-07:00.
expected_audience_countYesThe audience count you showed the person from campaign_preview.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already flag destructive=true, non-idempotent and open-world, but the description adds substantial context the annotations cannot convey: quota consumption of one email per recipient, irreversibility once sending begins, the expected_audience_count mismatch refusal, the first-campaign human review state, and the required API key scope 'send'. It does not describe what a successful response contains or the timing semantics of a future send_at, which keeps it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then consequences, then the required workflow, then edge cases — a sensible ordering with no filler sentences. It is dense enough that a skim could miss the review_pending caveat, slightly hurting scannability.

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 destructive, open-world mutation with no output schema, the definition covers safety, quota cost, approval protocol, and the exceptional review_pending outcome. Minor gaps remain around what a successful or scheduled response looks like and whether send_at in the past is rejected, but nothing critical to correct invocation is missing.

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 baseline is 3, but the description adds meaning beyond the schema for expected_audience_count by explaining it acts as a concurrency guard that causes refusal if the list changed materially. The other three parameters (id, confirm, send_at) are left entirely to their already thorough schema descriptions.

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 opening sentence states a specific verb and resource ('Schedules a drafted campaign to send to its audience'), and the prerequisite reference to campaign_preview implicitly separates it from preview/test/send-test siblings. An agent can distinguish this as the real, irreversible send step without opening any 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?

It gives an explicit ordered workflow: call campaign_preview first, disclose audience count and quota cost, obtain explicit approval, then call this with confirm. It also names the escape hatch (campaign_cancel before send_at) and the one case where retrying is wrong (review_pending).

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