Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Request business research

create_business_research_request
Idempotent

Starts durable background business research for large people searches, emailed Excel workbooks, or unanswered fast-search requests; takes the user's original request verbatim.

Instructions

Starts slow durable background research that runs for several minutes to hours: for more than 200 people, for an explicitly requested emailed Excel workbook or background task, or for a request the fast people search (find_people, up to 200 contacts in about 15 to 60 seconds, including a company's CIO or N people at each named company) could not answer. It takes the user's original request verbatim; the backend interprets count, roles, title equivalents, personal versus employer geography, industry and size, and discovers eligible companies itself. spec is optional legacy hints that never override the request. A company's headquarters is never treated as a person's location. The same idempotency_key returns the same request. contact_provider=treg selects TREG for an explicit provider comparison; otherwise the default contact database is used. Returns the backend acknowledgment with the goal id and state (for example waiting_dependency, waiting_budget or retry_wait); work continues after the connection closes. Named people and employers are never substituted, and contacts, emails and LinkedIn are never invented. Delivery follows the account's existing authorized channel and checks. 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>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "create_business_research_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
specNo
requestYes
config_idNo
research_depthNostandard
idempotency_keyYes
contact_providerNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the annotations (openWorldHint, idempotentHint, destructiveHint=false) by disclosing that work continues after the connection closes, that the response is an acknowledgment containing goal id and state (waiting_dependency, waiting_budget, retry_wait), and that idempotency_key makes the call replay-safe. Also states strong non-fabrication guarantees and that delivery uses the account's existing authorized channel with no prospect outreach. Slightly short of 5 because research_depth and config_id behavior go unmentioned.

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?

Front-loaded with the trigger condition and routing rule, which is the highest-value information, and every later clause (geography rule, no-substitution guarantees, channel constraints) adds distinct policy. It is dense and runs long as a single block, but little is truly wasted.

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 complex async research submission with a large nested spec, no output schema, and no annotation coverage of return shape, the description supplies the return contract and the background-continuation semantics. Missing are the meaning of config_id and when to choose research_depth=deep, both of which affect the call.

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?

Top-level schema coverage is 0%, so the description carries most of the burden and does explain request (verbatim user text), spec (optional legacy hints that never override the request), idempotency_key (same key → same request), and contact_provider=treg (explicit provider comparison). It leaves config_id and research_depth unexplained, which is a real gap for a 6-parameter tool.

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?

States a concrete verb and resource ('Starts slow durable background research') and immediately bounds it in time ('several minutes to hours'). It explicitly distinguishes itself from the sibling fast path find_people, including that tool's latency and capacity, so an agent can route without opening either schema.

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

Usage Guidelines5/5

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

Gives three concrete trigger conditions (>200 people, explicitly requested emailed Excel workbook/background task, or a request find_people could not answer) and names the alternative with its limits ('up to 200 contacts in about 15 to 60 seconds'). When-not guidance is implicit but strongly encoded in the fast-path comparison.

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