Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Find lookalikes

find_lookalikes
Idempotent

Finds people similar to a campaign's best customers, excludes existing customers, and adds found contacts with emails to the Golden List for research.

Instructions

Keeps the customer's best customers on the campaign (lookalike_seeds in research_options) and starts one people search for people like them who match the targeting: the same kinds of roles at the same kinds of companies, skipping the customers named. The people found with an email join the Golden List and are researched like everyone else; the search charges one credit per person delivered. Returns the campaign with view_in_producerspark. 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>",
      "seeds": "<seeds>"
    },
    "name": "find_lookalikes"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNo
seedsYesThe customer's best customers in their own words: company names, or people and their companies.
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?

Beyond the annotations it discloses real behavioral consequences: one credit charged per person delivered, discovered people with an email being enrolled in the Golden List and researched, the existing customers being skipped, the returned campaign view, and the meaning of 400 versus 404. That is exactly the cost/side-effect/error context annotations cannot convey.

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?

Every sentence carries information (behavior, cost, return, errors), so there is no padding, but the prose is dense and jargon-laden ('view_in_producerspark', 'Golden List', 'research_options') in a single run-on opening sentence. It is front-loaded on the core action but harder to parse than it needs to be.

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 mutating, credit-spending tool with no output schema and low schema coverage, the description covers side effects, billing, return shape, and error semantics well. The remaining hole is that the count parameter's meaning and default are never addressed, which matters because it drives both volume and credit spend.

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 only 33% (only seeds is documented in the schema), so the description has to compensate. It explains what seeds means in product terms (the customer's best customers in their own words, stored as lookalike_seeds in research_options) and ties them to the exclusion behavior. It leaves count and campaign_id unexplained beyond the implicit 'one credit per person delivered' hint, which is a genuine gap but a smaller one.

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 action chain: retains the supplied seeds on the campaign and launches a single people search for lookalikes matching the targeting, excluding named customers. That is far more than a restatement of the title, though it never names a sibling tool (find_people, deep_search) as the contrasting choice.

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: an agent can infer this is the tool for 'find more people like my existing best customers on this campaign.' There is no explicit when-not guidance or routing to alternatives such as find_people for non-lookalike sourcing, so the agent must infer the boundary.

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