Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Find people

find_people
Idempotent

Search for people by role, industry, location, company, technology, hiring title, or LinkedIn engagement and return matching contacts with titles, companies, emails, and verification details.

Instructions

Fast people search for any role, industry or location, taking the request in the user's own words. It runs as its own task on the account and this call returns within about 30 seconds: the contacts when the search has finished (most finish in 20 to 60 seconds), otherwise status still_running with progress (its message names the stage, how many of the requested people are found and the seconds so far, in one line for the person waiting) and next_step; a repeat call with the same idempotency_key returns the same search, never a second one, and the search keeps running in between. An open search returns up to 200 contacts; a search that names companies covers up to 100 of them. A conference speaker or attendee request also reads the event's published pages and can take several minutes, with a notice in the result meanwhile. Its coverage.event.listed_on counts the people each site named and each row's event_source is the page that named that person: when most came from sites other than the event's own, the reply states that plainly (for example, most names come from sponsor and partner pages announcing their sessions) and does not call them the event's own pages. When coverage.event.own_pages_note is set, give it in the reply as written. When coverage.condition_note is set, give it right after the count, as written, before the table, and never say every row met a condition it says is unconfirmed. Rows carry name, title, company, business email with its saved verification status, LinkedIn, location, fit, why and anything unverified. It filters on title, seniority, person and company location, industry, company size, named companies, the technologies a company uses (HubSpot, Salesforce, Applied Epic and most named software) and the roles it is hiring for. A request for the people who commented on or reacted to a company's or a person's LinkedIn posts ("people who commented on Gojiberry's LinkedIn posts") reads those posts from the last 90 days and returns up to 25 engagers, commenters first, each with what they did and the post in why, and coverage.engagement says how many posts and people were read; any other condition is judged from each record and listed as unverified when the record cannot confirm it. coverage.filters lists the technologies and hiring_titles that filtered the search and untracked_technologies it could not filter on. coverage reports requested versus returned, named employers with no contact record, per_company_default (when the request gave no number), count_step (when the search was sized first at no charge and paused), full_list (everyone who matched, with estimated_credits) and deep_search (people it could not place). status upgrade_required, credits.exhausted or coverage.held_for_credits above 0 mean the account's free prospects or credits are used up; upgrade_url is then the plans page. could_not_finish means the search failed on ProducerSpark's side. credits.remaining gives what is left. The account owner is emailed a summary with the workbook attached. Each result has view_in_producerspark (this search's page with its Excel download) and reply_must_end_with (that link as a ready line). In supporting chats the people also appear as cards with headshots; the cards carry no emails. No prospect outreach.

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": {
      "request": "<request>"
    },
    "name": "find_people"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestYes
config_idNo
idempotency_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A3.6/5.0
Behavior5/5

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

The description discloses extensive behavioral context beyond the annotations: task duration (~30 seconds), status handling, idempotency behavior, credit exhaustion states, coverage details, email summaries, and output fields like view_in_producerspark and reply_must_end_with. It even clarifies that cards carry no emails and no prospect outreach occurs. This is a very high level of transparency.

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?

The description is front-loaded with purpose but then becomes a dense wall of text with long, parenthetical sentences. Much of the detail is valuable, but it could be better organized (e.g., bullet points or clearer sections). It is adequately sized for the tool's complexity but not optimally concise.

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?

Given the tool's complexity (multiple modes, credit handling, error states) and the absence of an output schema, the description is nearly complete. It covers return values, edge cases, and response formatting. The only notable gap is the unexplained config_id parameter and lack of explicit sibling guidance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It hints that 'request' is in the user's own words and explains idempotency_key behavior. However, config_id is never mentioned, and the request parameter's natural-language expectation is only implied. Significant gaps remain.

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 states a specific verb and resource: 'Fast people search for any role, industry or location.' It clearly conveys the tool's core purpose. However, it does not explicitly distinguish itself from sibling tools like deep_search or full_list, so it falls short of the highest bar.

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?

The description implies usage through detailed scenarios (e.g., conference speaker requests, LinkedIn engagement) but never explicitly says when to use this tool instead of alternatives. There are no exclusions or named alternatives, leaving the agent to infer appropriate use cases.

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