Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Add prospect signal

add_prospect_signal
Idempotent

Records a first-party signal your own system knows about a Golden List prospect, turning it into their strongest research signal, reworking their scores, and triggering the prospect.signal webhook. Sends nothing.

Instructions

Records a first-party signal the customer's own system knows about a Golden List person: it joins their research as a found signal with the intent as evidence, becomes their strongest signal, reworks their scores, writes their {{signal_line}} for it, and the campaign's webhook hears prospect.signal. Review mode applies. Returns created (false when that keyword was already recorded for the person) and the person's research row. Sends nothing. 400 carries a plain reason; 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>",
      "candidate_id": "<candidate_id>",
      "intent": "<intent>",
      "keyword": "<keyword>"
    },
    "name": "add_prospect_signal"
  }
}

Input Schema

NameRequiredDescriptionDefault
intentYesWhat happened, in a sentence, for example 'Booked a demo from the pricing page'.
keywordYesA short label for the signal, for example demo_booked; one signal per person and keyword.
source_urlNoA link to the record or page behind it, when there is one.
campaign_idYes
candidate_idYesThe prospect's candidate_id from get_prospect_intelligence or signal_search rows.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A4/5.0
Behavior5/5

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

Beyond the annotations, the description discloses the full side-effect chain: the signal joins research, becomes the strongest signal, reworks scores, writes the signal line, and fires the prospect.signal webhook. It also clarifies 'Sends nothing', explains the idempotency semantics of created=false for a duplicate keyword, and maps 400/404 to their meanings — all context the annotations alone do not carry.

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?

The purpose is front-loaded and nearly every clause carries behavioral information rather than filler. The main weakness is the first sentence's run-on structure and the unexplained templated placeholder '{{signal_line}}', which an agent cannot interpret without outside knowledge.

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?

With no output schema, the description correctly covers the return shape (created plus the research row) and the 400/404 failure modes, which is what an agent needs to call and interpret it. The one gap is that 'Review mode applies' is stated without explaining what that changes operationally.

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 80%, so the baseline is 3, but the description adds meaning on top: intent is treated 'as evidence' and keyword is the dedupe key ('false when that keyword was already recorded for the person'). It does not touch source_url or candidate_id beyond what the schema already documents.

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 names a specific verb and resource ('Records a first-party signal ... about a Golden List person') and scopes it to signals the customer's own system already knows, which implicitly contrasts with the campaign-level sibling add_campaign_signal. It stops short of naming that sibling explicitly, so an agent must infer the boundary rather than read it.

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 by 'a first-party signal the customer's own system knows about a Golden List person' and the note that 'Review mode applies', which tells the agent the write may need approval. There is no explicit when-to-use-this-vs-alternative guidance against add_campaign_signal or update_campaign_signal, and no stated exclusions.

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