Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Search for signals

signal_search
Idempotent

Researches campaign prospects against target signals and writes each person's custom first email from a plain-language request, returning ready results.

Instructions

Researches people on a campaign's Golden List against its target signals and writes each one's custom first email, taking the request in the user's own words. People or companies it names are researched; otherwise the next N without results (default 10, at most 100). Uses the default campaign unless campaign_id is given; the campaign must be active. Each person costs 1 credit per signal (research_credits_per_prospect, in the result), charged only when every signal was answered, and takes about a minute. The call returns what is ready so far; while status is still_running a repeat call with the same idempotency_key and campaign_id returns the rest and never starts or charges a second search. Rows carry name, title, company, email, status (ready, no_signal, queued, running, held or failed; held means credits are used up), summary, strongest_signal, signals (fired, evidence, sources), facts with sources and, when a signal fired, the custom email (subject and body), which replaces Email 1 when the person is enrolled. Nothing is sent. Each result has view_in_producerspark and reply_must_end_with. 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": "signal_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
requestYes
campaign_idNo
idempotency_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations it discloses cost (1 credit per signal per person, charged only when every signal fired), latency (~a minute per person), partial-return/polling behavior, and the idempotency contract that a repeat call with the same idempotency_key and campaign_id resumes rather than re-charges. It also enumerates the status vocabulary, explains that 'held' means credits are exhausted, and confirms nothing is sent. This is exactly the write/charge/side-effect context the readOnlyHint=false annotation 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded in sentence one and nearly every clause carries operational information an agent needs (cost, timing, polling, statuses, return shape). It is a single dense paragraph of roughly 180 words, though, and would scan better split into behavior/cost/return groupings.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, non-read-only, open-world tool with no output schema and zero schema descriptions, the definition still covers cost model, async polling, idempotency, every status value, per-row return fields, and the destination of the generated email. An agent has enough to invoke it and interpret the response correctly on a first call.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must carry the load, and it does: request is described as free-form wording in the user's own words (including how N is expressed), campaign_id as default-campaign override with an active-campaign constraint, and idempotency_key as the resume handle paired with campaign_id. All three parameters gain meaning the bare schema does not provide.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a concrete verb+resource: research people on a campaign's Golden List against its target signals and write each one's custom first email. That is far more specific than 'search' and pins the tool to a particular artifact (Golden List, custom Email 1), so an agent can identify it without opening the schema.

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

Usage Guidelines4/5

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

It states prerequisites and selection conditions clearly: named people/companies are researched, otherwise the next N without results (default 10, cap 100), the default campaign is used unless campaign_id is given, and the campaign must be active. It also ends with 'No prospect outreach.' The only gap is that it never names a sibling alternative (e.g. deep_search or find_people) for the case where this tool is the wrong choice.

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