Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Run deep search

deep_search
Idempotent

Retries people a find_people search could not place by checking alternate spellings and the web, returning confirmed or possible additions with progress status and credit coverage.

Instructions

Slower second pass over the people a find_people search (its goal_id) could not place: it retries other spellings of each name, then the web, and returns only the additions, usually within a few minutes. Each call returns within about 30 seconds: the additions when it has finished, otherwise status still_running with progress (a one-line message for the person waiting) and next_step, and a repeat call with the same goal_id returns the same deep search. Each row has match: confirmed (a contact record has the requested name and employer; costs credits_per_find credits) or possible (an unconfirmed profile: free, no email, a name to check rather than a finding). A row's listed_name is the person it replaces from the first results. coverage gives confirmed, possible, not_found, still_without_email and credits_charged; credits.remaining gives what is left. One search has one deep search, so a repeat call while status is still_running never starts or charges a second. decline=true searches and charges nothing and emails the first results as they stand (status results_emailed). status upgrade_required or coverage.held_for_credits above 0 mean credits are used up; upgrade_url is the plans page. The account owner is emailed a summary with the updated workbook. Each result has view_in_producerspark and reply_must_end_with. 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": {
      "goal_id": "<goal_id>"
    },
    "name": "deep_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
declineNo
goal_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations, it discloses credit charging, timing, polling behavior, idempotency by goal_id, decline semantics, upgrade_required handling, emailed summaries, and UI card behavior. This is unusually thorough for a tool that mutates account credits.

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 and information-dense, but it is a long, run-on paragraph that mixes invocation behavior, return values, credit rules, and UI details. It earns most of its length, yet the structure could be clearer with separation between usage, behavior, and return semantics.

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, credit-charging, asynchronous tool with no output schema, the description covers timing, statuses, return fields, coverage metrics, credit semantics, and failure paths. An agent has enough information to call it correctly and interpret the results.

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?

With 0% schema description coverage, the description does the work: goal_id is the original find_people search identifier, and decline=true searches without charging and emails existing results. It could be slightly clearer about goal_id's exact relationship, but both parameters are meaningfully explained.

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 description names a specific verb and resource: a slower second pass over people that a find_people search could not place, retrying spellings and the web. It explicitly distinguishes itself from find_people by framing itself as the follow-up pass keyed by the original goal_id.

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 clearly establishes the use case: run this after find_people has left people unplaced. It also explains the decline=true alternative and the repeat-call behavior, though it does not explicitly state when not to use the tool or name other alternatives.

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