Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Activate campaign

activate_campaign

Starts a campaign to add matching people to a Golden List from a search or watched signals, using a confirmation step before activation; no emails are sent.

Instructions

Activates a campaign. With no signal that finds people, it runs as a static list: a search adds the first 100 people who match the targeting to the Golden List (one credit per person found). Otherwise it starts watching its signals. When a signal that finds people fires, each person behind it who fits the targeting is looked up and added to the Golden List, up to the campaign's daily cap (20 a day unless changed), and the campaign's other signals are checked for that person; a custom first email is written for the customer to review, which replaces Email 1 when that person is enrolled. Costs one credit per person added and, per person checked, 1 credit per signal (research_credits_per_prospect), charged only when every signal was answered. Nothing is sent and nobody is enrolled. Needs targeting; a 400 error names what is missing. The first call activates nothing and returns needs_confirmation, will_happen (a plain description of what will start) and confirmation; activation happens only on a second call with the same campaign_id and that confirmation. 404 means the campaign is unknown or archived. Returns view_in_producerspark.

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": {
      "campaign_id": "<campaign_id>"
    },
    "name": "activate_campaign"
  }
}

Input Schema

NameRequiredDescriptionDefault
campaign_idYes
confirmationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A4.1/5.0
Behavior5/5

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

With annotations only declaring readOnly=false/destructive=false/openWorld=true/non-idempotent, the description adds substantial behavior: credit costs (1 per person, 1 per signal checked, only when all signals answered), a 20/day default cap, a custom email written for review that replaces Email 1, the absence of sends and enrollments, and the two-call confirmation gate. The 400/404 semantics and the view_in_producerspark return are also disclosed, which the annotations do not cover.

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

Conciseness3/5

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

Sentences are long and clause-chained, packing credit math, caps, email substitution, and error codes into single run-ons. Crucially, the two-call confirmation protocol — the most behaviorally important fact — appears near the end rather than being front-loaded, so an agent skimming the opening could call it once and assume success.

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 two-parameter tool with no output schema and high behavioral complexity, the description covers preconditions, side effects, credit charging rules, error codes, the confirmation handshake, and the return value. It is close to complete; what is missing is any statement of what happens if the caller abandons after the first call, or whether a pending confirmation expires.

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 0%, so the description carries the burden, and it does explain the non-obvious `confirmation` parameter: omit it on the first call, then pass back the returned value with the same campaign_id once the user has read will_happen and said yes. `campaign_id` receives no explicit meaning beyond being the identifier used for sameness matching, which is the only shortfall.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb and resource, and the body clarifies that 'activation' means signal-watching plus Golden List population rather than sending. The clause 'Nothing is sent and nobody is enrolled' implicitly separates it from start_campaign_sending and enroll_campaign_people without naming them, so an agent can distinguish it but must infer the contrast.

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?

Usage conditions are stated concretely: targeting is required, a 400 error names what is missing, 404 means unknown or archived, and the mandatory two-call confirmation sequence is spelled out. The gap is that no sibling alternative is ever named, so an agent must derive from 'nothing is sent' which other tools to pick for sending or enrollment.

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

Deploy Server

Other Tools