Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Get prospect intelligence

get_prospect_intelligence
Read-onlyIdempotent

Retrieve a campaign's Golden List prospect data: signal research, custom emails, scores, review state, freshness, enrollment blockers, status counts and filters. Read-only; no research starts.

Instructions

The signal research and custom emails already on a campaign's Golden List, newest first, with counts (ready, no_signal, queued, running, held, failed, could_not_check, and pending prospects not yet researched), optionally filtered by status. Rows have the same shape as signal_search rows and carry scores (fit 0 to 1, intent 0 to 3, total, each with its reason), review (waiting or approved under review mode), fresh (false once older than 90 days) and enrollment_block (why the person is not enrolled now, or null). Reads only; starts no research.

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": "get_prospect_intelligence"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
statusNoFilters rows to one state: ready, no_signal, queued, running, held, failed or could_not_check. Omitted: all rows.
campaign_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered by structured data. The description does add substantial value beyond that: ordering, the eight count buckets, score ranges (fit 0-1, intent 0-3, total) with reasons, the 'waiting or approved' review states, the 90-day freshness rule, and the meaning of enrollment_block. This is close to a 4, but it says nothing about pagination or how counts are delivered, and the 'pending' count bucket is not represented among the filterable statuses, which can confuse an agent mapping counts to filters.

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?

It is one dense sentence, but the key facts (what the list is, ordering, counts, filter, row shape, read-only) are front-loaded and every clause carries information rather than restating the name. The heavy parenthetical enumerations make it harder to scan than it needs to be, but nothing is genuinely wasteful.

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 carries the return-value burden and does so well: field meanings for scores, review, fresh and enrollment_block are all explained, so an agent can interpret rows without guessing. Gaps remain around pagination/limit behavior and around the unexplained cross-reference to an unspecified 'signal_search' row shape.

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

Parameters3/5

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

Schema coverage is only 33%, and only the status parameter is documented in the schema. The description reinforces status semantics (optionally filtered by status) but adds no meaning for campaign_id or for limit (bounds 1-500, default 100) — an agent gets no guidance on page size or how to page through a large Golden List. The missing half of the parameters is not compensated for, so this stays at the minimum-viable level.

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 the concrete resource (signal research and custom emails on a campaign's Golden List) plus its scope, ordering ('newest first') and status-filtering behavior, so the agent knows exactly what comes back. It also differentiates from the sibling signal_search by saying rows have the same shape, though it never explicitly frames the verb ('returns/lists') or distinguishes itself from get_prospect_list.

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 closing 'Reads only; starts no research' gives one useful exclusion (this is not the tool that triggers research), and 'optionally filtered by status' implies the filtering use case. However, there is no explicit statement of when to choose this over get_prospect_list or signal_search, and no prerequisites are stated, leaving the agent to infer routing.

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