Hermes Micro-Agent

Verify a USDC payment

verify_payment

Read-onlyIdempotent

Verify a USDC payment on Base before retrying a paid request; the free pre-retry check between price_task and execute_task.

Free to call, no authentication, no side effects. Never raises - always HTTP 200 with the verdict in the body, not the status.

Parameters: the hash must be the same one set in the X-Payment header; set min_cents to the task's exact price, since a value above it makes a correct payment read as invalid.

When to use: after sending USDC, before retrying. If valid, retry with the same hash; if not, do not.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tx_hash": "<tx_hash>"
    },
    "name": "verify_payment"
  }
}

Input Schema

Name	Required	Description	Default
`tx_hash`	Yes	Base transaction hash (0x-prefixed) of the USDC payment to verify, e.g. the hash your wallet returned after sending.
`min_cents`	No	Minimum acceptable payment amount in USDC cents (1 cent = 0.01 USDC). Default 1000 = 10 USDC. The payment must be worth at least this much to pass, otherwise valid is false.

Output Schema

Name	Required	Description
`error`	No
`valid`	No	true when the payment is confirmed
`amount`	No
`reason`	No
`tx_hash`	No
`receiver`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A5/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), yet the description adds genuinely non-obvious behavior: free to call, no authentication, and critically 'Never raises - always HTTP 200 with the verdict in the body, not the status.' That last detail prevents a common agent failure mode of inferring validity from the HTTP status.

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?

Front-loaded with purpose, then behavior, then parameters, then when-to-use — four short blocks with zero filler. Every sentence carries operational information; nothing is restated from annotations or schema.

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

Completeness5/5

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

For a two-parameter read-only verification tool with an output schema, this covers everything needed to call it correctly: where it sits in the workflow, the header/hash coupling, the min_cents pitfall, and the fact that the verdict arrives in the body. Return-value shape is left to the output schema, as appropriate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description adds meaning for both parameters beyond the schema: tx_hash must be the same hash sent in the X-Payment header, and min_cents must be set to the task's exact price because 'a value above it makes a correct payment read as invalid' — a non-obvious trap the schema's 'at least this much' phrasing does not convey.

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

Purpose5/5

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

States a specific verb and resource ('Verify a USDC payment on Base') and situates it precisely in the workflow as 'the free pre-retry check between price_task and execute_task', naming two siblings. An agent can distinguish this from execute_task or get_job_status without opening any schema.

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

Usage Guidelines5/5

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

Explicit 'When to use: after sending USDC, before retrying', plus branching instructions on the outcome: 'If valid, retry with the same hash; if not, do not.' This is a complete when-to-use, when-not-to-use and next-step contract with no inference required.

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

All Hermes Micro-Agent 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.

Resources

Need Help?