Skip to main content
Glama

leadquasar

by io.github.si-imtiaz

count_businesses

Count verified US B2B businesses in the LeadQuasar database matching an industry, state and/or city, with how many have an email address and a phone number. Use this to answer questions like 'how many managed service providers are there in Texas' or 'how many dentists in Chicago have a business email'. Returns real counts from 7.5 million live records.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cityNoUS city name.
stateNoUS state, either full name ("Texas") or two-letter code ("TX").
industryNoIndustry or business type in plain words, e.g. 'managed service provider', 'dentist', 'HVAC contractor', 'plumbers'. Everyday wording is resolved to the stored categories, so 'HVAC contractor' finds HVAC and 'plumbers' covers both Plumbers and Plumbing. The response reports which category it matched.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedInput schema / properties / industry / description
      Previous value: -"Industry or business type in plain words, e.g. 'managed service provider', 'dentist', 'HVAC contractor'. Matched against industry and category."New value: +"Industry or business type in plain words, e.g. 'managed service provider', 'dentist', 'HVAC contractor', 'plumbers'. Everyday wording is resolved to the stored categories, so 'HVAC contractor' finds HVAC and 'plumbers' covers both Plumbers and Plumbing. The response reports which category it matched."
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description must carry behavioral weight. It does so by saying counts are real rather than estimates, data is from 7.5 million live records, and businesses are verified US B2B. It stops short of describing the response format or any limitations, but the operation is a low-risk read-only count.

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 sentences with the action verb front-loaded and no wasted words. The examples are compact and illustrative, and the scope facts ('7.5 million live records') justify the tool without bloating the description.

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 simple count tool with only optional parameters, the description covers purpose, filters, and the main output dimensions (total count, email count, phone count). Since there is no output schema, it could be more explicit about the exact response shape, but an agent has enough to invoke correctly.

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?

The schema already documents all three parameters at 100% coverage, setting the baseline at 3. The description adds useful semantic context by combining filters ('industry, state and/or city') and by showing the email/phone count dimension implied by examples, which helps an agent understand how the parameters compose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Count verified US B2B businesses... matching an industry, state and/or city,' and closes with 'Returns real counts,' which separates it from the record-returning search_businesses sibling. It does not name sibling tools explicitly, so it falls just short of full sibling differentiation.

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?

'Use this to answer questions like...' provides concrete usage examples that map natural-language questions to parameters. It does not state when NOT to use it or direct the agent to search_businesses for record-level queries, so exclusions are missing.

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

All leadquasar toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation4/5

count_businesses and search_businesses both query the same database with similar filters, but their intents are clearly separated: one returns aggregate counts and the other returns sample records. list_industries is distinctly for exploring available industry categories. The overlap between counting and searching is minor and well explained by the descriptions.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case: count_businesses, list_industries, search_businesses. The verbs are specific and distinct, and the nouns clearly indicate what is being acted on. This makes the naming predictable and easy to learn.

Tool Count4/5

With 3 tools, the server is minimal but not inadequate—it covers the core needs of exploring industries, counting matches, and viewing samples. For a narrow, read-only database querying purpose, this is a reasonable scope. It is slightly on the lean side but each tool earns its place.

Completeness4/5

The surface covers the main workflows: discover available industries, count matching businesses, and retrieve sample records. The obvious gap is that contact details are never returned, but that is an intentional design choice stated clearly in search_businesses. Minor enhancements like pagination or state/city listing would help, but agents can accomplish the stated exploration goals with the given tools.

Resources