Skip to main content
Glama

67Leads

Request a list we don't carry

request_build
Idempotent

Ask for a niche and place that count_leads shows as empty or thin. Stores the request (deduped, a few a day per caller) and returns how many people asked for the same list. Does not build a list on the spot. Free.

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": {
      "state": "<state>"
    },
    "name": "request_build"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoPlain-English search, e.g. 'roofers in Dallas TX with no website'. Explicit fields below override what the sentence says.
cityNo
emailNoWhere to send word when it's built, if email alerts are on.
nicheNoA niche id or plain words, e.g. 'pool builders'.
stateYesUS state, code or name. Required.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations declare a non-read-only, idempotent, non-destructive write, and the description supplies exactly the context that annotations can't: dedup behavior, a rate limit ("a few a day per caller"), that the return value is a demand count from other callers, and that it is free. It also clarifies the side effect is a stored request rather than an immediate build, which is the detail an agent most needs before calling.

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?

Four short sentences, front-loaded with the trigger condition, each carrying distinct information (trigger, side effect, return value, cost). "Free" is terse and useful rather than filler; nothing is redundant with 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?

For a five-parameter write tool with no output schema, the description covers trigger, side effect, rate limit, and the shape of the response (a count of duplicate requests). It stops short of saying what the response looks like structurally or whether the count is scoped globally versus by region, a small gap but not a blocking one.

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 coverage is 80% and the schema already explains q, email, niche, and state including the override rule for explicit fields. The description only restates the niche/place concept and adds no format, enum, or validation detail beyond the schema, so the baseline of 3 applies.

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?

"Ask for a niche and place that count_leads shows as empty or thin" names a specific action and resource, and pins the trigger condition to a named sibling. "Does not build a list on the spot" preempts the most likely misread of a tool called request_build.

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?

The when-to-use condition is explicit (coverage that count_leads reports as empty or thin), and the negative case is stated (no on-the-spot list build). What's missing is routing for the adjacent cases — it never says what to reach for when the niche is already covered, leaving the agent to infer that search_leads or export_leads is the alternative.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources