Novarithm Agent Hub: trust and commerce checks

fragrance_check

[PAID $0.15 USDC/call, x402, eip155:8453] Risk signals for a fragrance listing: sales channel, price per ml, listing words, seller domain and EU Safety Gate. Does not authenticate a physical bottle. Provide url, or brand and seller_domain.

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": "fragrance_check"
  }
}

Input Schema

Name	Required	Description
`url`	No	Listing / product page URL
`brand`	No	Brand (when no url)
`price`	No	Listed price
`product`	No	Product title as listed, e.g. Sauvage EDT 100 ml
`size_ml`	No	Bottle size in ml (else read from the title)
`currency`	No	ISO 4217 currency of price
`batch_code`	No	Batch code printed on box/bottle
`seller_domain`	No	Seller website domain (when no url)

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 24, 2026
- addedInput schema / properties / price / minimum
```
Added value: +0
```
- addedInput schema / properties / size_ml / maximum
```
Added value: +1000
```
- addedInput schema / properties / size_ml / minimum
```
Added value: +1
```
AddedOct 24, 2026

TDQS

A3.9/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose two things an agent critically needs: this is a paid call ($0.15 USDC, x402, eip155:8453) and it will not verify a physical bottle. It stops short of describing the response shape or what happens when inputs are partial, which is a real gap given the absence of an output schema.

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?

Four compact clauses in three sentences: cost/protocol, what is returned, what is not returned, and required inputs. Every sentence carries non-redundant information and the cost constraint is front-loaded.

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 8-parameter, no-annotation, no-output-schema tool, the description covers the payment precondition, the input contract, and the negative capability. The remaining hole is the return payload — 'risk signals' is enumerated as topics but the agent gets no sense of verdict format or severity encoding.

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?

Schema coverage is 100%, so baseline is 3; the description earns an extra point by supplying the combination logic the schema cannot express — with zero required parameters, 'Provide url, or brand and seller_domain' tells the agent which alternative input sets are valid.

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?

Names the resource precisely (a fragrance listing) and enumerates the concrete signals returned: sales channel, price per ml, listing words, seller domain, EU Safety Gate. It also draws a scope boundary with 'Does not authenticate a physical bottle.' It never names a sibling such as pre_purchase_check or seller_reputation, so differentiation is left to inference.

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?

The only usage instruction is input-shape guidance: 'Provide url, or brand and seller_domain.' There is no statement of when an agent should reach for this tool instead of pre_purchase_check, seller_reputation, or gtin_recall, so the routing decision is implied rather than specified.

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 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.