Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Find mobile numbers

find_mobile_numbers
Idempotent

Look up mobile phone numbers in the contact database for people from a finished search or campaign Golden List, with a confirmation preview and credit cost before charging.

Instructions

Looks up mobile phone numbers in the contact database for the people of a finished find_people search or other task (goal_id), or of a campaign's Golden List (campaign_id). Each mobile number found costs credits_per_number credits (8); people with no mobile number, or no contact database record, cost nothing and are marked unavailable. A call without confirm=true looks nothing up and returns needs_confirmation, will_happen (who would be looked up and the most it can cost) and the account's credits_left. With confirm=true the lookup starts and the call returns within about three minutes with status finished or still_running and the people's rows: mobile_phone, phone_status (a number's status, unavailable or lookup pending), phone_dnc (true when the number is on the Do Not Call list, false when checked and absent, null when not checked), phone_confidence, phone_source and phone_date. A repeat call while a lookup runs never starts or charges a second one. status upgrade_required means credits are used up; upgrade_url is then the plans page. No prospect outreach.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_mobile_numbers"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNo
goal_idNo
campaign_idNo
idempotency_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: pricing (credits_per_number = 8, free for people with no number or no record), the preview payload contents, the ~3 minute return window, possible statuses (finished, still_running, upgrade_required), and the upgrade_url fallback. It also confirms the idempotentHint claim by stating a repeat call during a running lookup never starts or charges a second one, and it discloses the Do Not Call/phone_status semantics of returned rows. No contradiction with destructiveHint=false or openWorldHint=true.

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 purpose and the two id sources, then the cost and confirm semantics. The long enumeration of return fields is dense but justified given there is no output schema. A few clauses (e.g., parenthetical restatements of phone_dnc) could be tightened, but nothing is wasted.

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?

With no output schema, the description supplies the return shape (mobile_phone, phone_status, phone_dnc, phone_confidence, phone_source, phone_date) plus the status outcomes and error path. For a credit-charging, asynchronous lookup with four params, an agent has everything needed to call it correctly and interpret the response.

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?

Schema description coverage is 0%, so the description must carry parameter meaning, and it does for confirm (preview vs. execute), goal_id and campaign_id (which population is looked up). The fourth parameter, idempotency_key, is never mentioned, leaving its purpose and expected usage undocumented.

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 specific verb and resource ('looks up mobile phone numbers in the contact database') and immediately scopes the two supported populations via goal_id (a finished find_people search or other task) and campaign_id (a campaign's Golden List). An agent can distinguish this from find_people or list-oriented siblings 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?

Explains the intended input sources and prescribes the two-step workflow: a call without confirm=true is a dry run returning needs_confirmation and will_happen, and only confirm=true starts the lookup. It also excludes a use case ('No prospect outreach'). It does not name a sibling alternative for the people it cannot find, but the when-to-use context is clear.

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