Skip to main content
Glama

Agent trust

agent_trust

Agent trust score. Check before you pay another agent: pay / caution / avoid with the two strongest reasons and a 0-100 trust score, from observed data: operator (ERC-8004), distinct outside payers read on chain, a live probe of its x402 offer, uptime, verified Hyperliquid record, agent bond, OFAC. Pass ONE of url / address / agent. $0.005 (5 free checks a day at https://apexfaucet.xyz/api/agent-trust).

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": "agent_trust"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNothe x402 endpoint you are about to pay (https://...)
agentNoor its ERC-8004 agent id on Arc
addressNoor the seller payTo / agent wallet (0x...)
paymentNoa signed x402 payment (the same base64 payload you would put in the PAYMENT-SIGNATURE header). Pass it here and the purchase completes inside this tool call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
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 well: it discloses the evidence sources (operator/ERC-8004, on-chain distinct outside payers, a live probe of the x402 offer, uptime, Hyperliquid record, bond, OFAC), the price of $0.005, and the free tier. Crucially it warns that passing a signed payment completes the purchase inside the call — a real side effect an agent must not trigger accidentally. It does not cover latency, failure modes for an unknown agent, or whether calls are idempotent.

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 verdict and the decision it supports, then evidence sources, then input constraint, then price — a sensible priority order in three dense sentences. The evidence-source enumeration and the faucet URL are a little compressed into one long clause, but nothing is genuinely redundant.

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?

No output schema exists, and the description compensates by naming the return contents (verdict, two strongest reasons, numeric score). Inputs, cost, and the in-call payment path are all covered; what is missing is behavior for unresolvable/unknown agents and any indication of response time or caching.

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 the baseline is 3, but the description adds a constraint the schema does not encode: 'Pass ONE of url / address / agent,' which is absent since required is empty and there is no oneOf. It also reiterates the payment payload as the mechanism to complete the purchase in-call, reinforcing the schema's meaning.

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 concrete verb+resource ('Agent trust score' checked before paying another agent) and specifies the returned verdict (pay/caution/avoid), the two strongest reasons, and a 0-100 score. The output shape is clear enough to distinguish it from generic reputation siblings, though it never names which sibling to prefer (e.g. arc_trust_check, arc_agent_reputation).

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?

'Check before you pay another agent' gives an explicit trigger condition tied to a concrete decision point, which is stronger than most. It stops short of naming an alternative tool or describing when this check is unnecessary (e.g. already-known counterparties), so it is clear context without exclusions.

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