Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Add campaign signal

add_campaign_signal
Idempotent

Add a customer-worded signal to a campaign, keep existing signals, and convert it into source-specific searches; uncheckable signals are declined with a reason.

Instructions

Adds one target signal, in the customer's words, to a campaign and keeps its other signals. The backend turns it into one search per source it can be checked from (website, news, event, job postings, LinkedIn engagement: who posted, commented or reacted about a keyword, on a company page's posts or on a person's posts, read from public posts); a line nothing can check comes back declined with the reason. Returns the campaign with signal_items, each with its summary (what will be searched), check_from and checkable, and view_in_producerspark. On an active campaign, a changed set of signals makes every prospect due for research again (three first); nobody is charged twice for a person. 404 means the campaign is unknown or archived.

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>",
      "text": "<text>"
    },
    "name": "add_campaign_signal"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesOne signal in the customer's words, verbatim; it becomes one search per source it can be checked from.
campaign_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A3.9/5.0
Behavior5/5

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

Well beyond the annotations: the description discloses that the backend fans one signal into one search per source, that uncheckable signals are declined with a reason rather than silently dropped, the response shape (signal_items with summary, check_from, checkable, view_in_producerspark), the side effect that a changed signal set on an active campaign re-queues prospects for research ('three first'), the billing guarantee ('nobody is charged twice'), and the meaning of 404. Annotations only say write + idempotent + non-destructive, so this narrative adds real substance.

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?

Purpose is front-loaded in the first clause, which is good, but the rest is a single dense run-on with stacked parentheticals and em-dashes that is hard to scan. Every fact is arguably useful, yet a short bulleted split (behavior / response / side effects / errors) would deliver the same content far more legibly.

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 mutation with no output schema, the definition is unusually complete: it covers the transformation, the return shape, cost implications, prospect re-research side effects, and the 404 case. Remaining gaps are narrow — what happens when every candidate source is uncheckable (full failure vs. partial decline) and any permission or campaign-state prerequisites.

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 50%: text is documented, campaign_id is not (only exclusiveMinimum: 0). The description compensates partly by explaining what text becomes downstream (one search per source, verbatim wording) and by giving campaign_id meaning through the 404 case ('campaign is unknown or archived'). It never states that campaign_id refers to an existing live campaign or what 'active' versus draft means for the side effects.

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 description opens with a specific verb and resource: 'Adds one target signal, in the customer's words, to a campaign and keeps its other signals.' That phrasing implicitly distinguishes it from update/delete siblings by stressing additive, non-replacing behavior. It stops short of naming any sibling explicitly (e.g. add_prospect_signal, update_campaign_signal), so differentiation depends on inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is implied rather than stated: the agent learns a signal must be 'in the customer's words' and that uncheckable lines will be declined, which governs what to pass. There is no explicit 'use this instead of update_campaign_signal when...' routing and no mention of prerequisites such as campaign ownership or state beyond the 404 note. Adequate but leaves selection guidance to inference.

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