Skip to main content
Glama
Sign In

Company Facts

by dev.companyfacts
OverviewDiscussionsAdmin

Search the companies we track

company_search
Read-onlyIdempotent

Finds companies across everything we track: newly formed New York, Colorado, Oregon, Connecticut and Pennsylvania businesses with a website found with proof, and every FDIC-insured bank in any state. Filter by state, source, city, name, formation date, technology on their site (for example Shopify or WordPress), whether they publish a phone, role inbox or contact page, and hiring. Returns register details, website, technologies and job board, newest first. No match is never charged.

Input Schema

NameRequiredDescriptionDefault
hasNoKeep companies whose site publishes these: any of phone, role_email, contact_page.
cityNoCity as the register gives it, not case sensitive.
nameNoPart of the legal name.
techNoTechnology names on the home page, comma separated; all must be present.
limitNoCompanies per page, 1 to 100. Default 25.
stateNoTwo-letter US state codes, comma separated.
hiringNotrue for companies with open roles on a job board we read, false for none.
offsetNoSkip this many, for the next page.
sourceNoWhere the company came from: state_register (new businesses) or fdic (banks), comma separated.
formed_sinceNoFormed on or after, YYYY-MM-DD.
formed_untilNoFormed on or before, YYYY-MM-DD.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / source
      Added value: +{
+  "description": "Where the company came from: state_register (new businesses) or fdic (banks), comma separated.",
+  "type": "string"
+}
    • changedInput schema / properties / state / description
      Previous value: -"Any of NY, CO, OR, CT, PA, comma separated."New value: +"Two-letter US state codes, comma separated."
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, open-world and non-destructive, so the bar is lower. The description adds genuinely non-structured behavior: results come back 'newest first', the payload includes register details, website, technologies and job board, and 'No match is never charged' discloses a billing trait an agent would otherwise not know.

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 the core capability, followed by corpus scope, filters, and return shape in three tight sentences. The long middle clause enumerating states is a bit list-heavy but every element carries information an agent needs to judge coverage.

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 an 11-parameter, no-output-schema tool, the description covers what the corpus contains, what can be filtered, what is returned, and result ordering. Only the pagination story (limit/offset interplay) is left entirely to the schema, which is acceptable since those fields are documented there.

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 the schema already explains every filter including the `has`, `tech` and `source` vocabularies. The description only restates the filter categories in prose (e.g. 'technology on their site (for example Shopify or WordPress)'), adding illustration but little new semantics beyond the schema.

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?

States a specific verb and resource ('Finds companies') and scopes the corpus precisely: newly formed businesses in five named states with a verified website, plus every FDIC-insured bank. That corpus definition implicitly separates it from siblings like search_company_registry or company_lookup, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the enumeration of filters ('Filter by state, source, city, name, formation date, technology...'), so an agent can infer this is the broad filtered-search entry point. However, it never states when to prefer company_lookup, search_company_registry, new_businesses, or compare_companies, nor any exclusions or prerequisites.

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

All Company Facts toolsInspect
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.

Resources