LeadMerlin

Start a lead search

start_search

Start an async search for local businesses by keyword in up to 5 locations, then enrich each one. Spends 1 credit per business with a website (website-less and off-niche listings are free). Returns a job_id; poll get_job. Call once per search: every call starts a new paid job.

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": {
      "keyword": "<keyword>",
      "location_codes": "<location_codes>"
    },
    "name": "start_search"
  }
}

Input Schema

Name	Required	Description
`keyword`	Yes	Business niche, e.g. "plumber"
`max_leads`	No	Cap on businesses charged and enriched. Strongly recommended.
`strictness`	No	Niche filter. moderate (default) drops keyword coincidences; strict also drops adjacent trades.
`location_codes`	Yes	Codes from find_locations
`phone_line_type`	No	Look up mobile/landline/VoIP for each main phone (default true, monthly plan allowance).
`exclude_exported`	No	Skip businesses this account already exported (not charged).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare non-read-only, non-idempotent, open-world, non-destructive, but the description adds the crucial cost model (1 credit per business with a website; website-less and off-niche listings free) and the operator-facing consequence of non-idempotency (each call starts a new paid job). It does not state rate limits or how long a job takes, which is a minor gap for an async tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Three tight sentences, front-loaded with what the tool does, then cost, then the follow-up call and the single-call warning. No filler and no repetition of the title.

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?

Covers the essentials for an async, credit-spending job starter: what it produces (a job_id), what to do next (poll get_job), and what it costs. With no output schema, it adequately substitutes by naming the return value, though it says nothing about failure modes or how long a job typically runs.

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 description coverage is 100%, so all six parameters including enums and defaults are already documented. The description adds only indirect meaning (the 'up to 5 locations' bound and the credit clause that clarifies what max_leads is capping), which is useful but thin beyond the schema.

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, resource, and scope: 'Start an async search for local businesses by keyword in up to 5 locations, then enrich each one.' The async/job-based nature plus the enrichment step makes it distinguishable from get_results and get_job without opening their schemas.

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?

Names the follow-up action explicitly ('poll get_job') and imposes a real usage constraint: 'Call once per search: every call starts a new paid job.' Together these tell the agent both the next step and the condition under which it must not re-invoke the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All LeadMerlin tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.