Skip to main content
Glama
Sign In

Novarithm Agent Hub: trust and commerce checks

by com.novarithm.www
OverviewDiscussionsAdmin

fact_company

[PAID $0.02 USDC/call, x402, eip155:8453] Official company record from the French state registry: legal name, SIREN, SIRET of the head office, activity code, address, city, employee band, creation date and open establishments. Signed, so the buyer can prove the record came from the registry at a known instant.

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": "fact_company"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoCompany name or fragment to search
sirenNoExactly 9 digits, exact lookup

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral disclosure burden and does provide useful context: paid call cost, x402 mechanism, network eip155:8453, and signed provenance at a known instant. It still omits edge-case behavior such as what happens when a name search matches multiple companies, but it discloses key operational traits.

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?

The description is compact and front-loads the paid-call context before stating the resource and returned fields. It is dense but not bloated; the signing sentence earns its place by explaining provenance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter registry lookup with no annotations and no output schema, the description gives a useful field list and payment context. However, it does not explain result shape, multiple-match behavior, or whether at least one of q/siren is required in practice.

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 100%, and both parameters are already documented as a company name/fragment search and an exact 9-digit SIREN lookup. The description does not add further meaning or constraints beyond what the schema provides, so the baseline of 3 is appropriate.

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 resource and scope: an official company record from the French state registry, with named fields such as legal name, SIREN, SIRET, activity code, and address. It does not explicitly distinguish this from related fact tools such as fact_key or fact_verify, so it is strong but not fully sibling-differentiated.

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

Usage Guidelines2/5

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

The description does not say when to use this tool versus alternatives, nor does it name exclusions or prerequisites beyond the payment tag. An agent can infer it is a company lookup, but there is no explicit usage routing.

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

All Novarithm Agent Hub: trust and commerce checks 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