Hermes Micro-Agent

Refund a job

refund_job

DestructiveIdempotent

Refund one job's payment to its sender, or issue an account credit.

Destructive and irreversible: funds go back on Base and the job is marked refunded. No undo.

Behavior: refunds on-chain when a private key is configured, else credits the sender. Returns a refund hash, 'credit_only', or 'job_not_found'. Refunding twice is safe.

Parameters: an unknown key returns job_not_found and moves nothing.

When to use: when a paid job failed. Check get_job_status first; use get_credit_balance to see if a refund became credit.

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": {
      "job_key": "<job_key>"
    },
    "name": "refund_job"
  }
}

Input Schema

Name	Required	Description	Default
`job_key`	Yes	Job key to refund, from execute_task or list_jobs. Required.

Output Schema

Name	Required	Description
`error`	No
`result`	Yes	refund tx hash, 'credit_only', or 'job_not_found'
`job_key`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, yet the description still adds material context: funds move on Base, the job is marked refunded, there is no undo, and on-chain vs. credit behavior depends on whether a private key is configured. It also anticipates the ambiguous case ("Refunding twice is safe") and the invalid-key case, which is exactly the behavior an agent needs before committing to a mutation.

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-loads the action and the destructive warning, then uses short labeled sections (Behavior, Parameters, When to use) that map to the questions an agent asks in order. Wording is tight; the only repetition is "irreversible" and "No undo," which reads as deliberate emphasis on the highest-risk fact.

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 one-parameter, high-stakes mutation, the description covers activation conditions, side effects, irreversibility, idempotency, failure semantics, and follow-up tools. An output schema exists, so the brief mention of return values (refund hash, 'credit_only', 'job_not_found') is more than enough.

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?

With one parameter at 100% schema coverage, the schema already explains what job_key is and where to get it, so the baseline is 3. The description adds meaning the schema does not: an unknown key returns job_not_found and moves nothing, which tells the agent the parameter is validated before any funds move.

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?

Opens with a specific verb and resource plus its two possible outcomes: "Refund one job's payment to its sender, or issue an account credit." That scope distinguishes it clearly from siblings like get_credit_balance and cancel_job without the agent needing to open a 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?

Provides an explicit trigger ("when a paid job failed"), a prerequisite ("Check `get_job_status` first"), and a follow-up route ("use `get_credit_balance` to see if a refund became credit"). An agent has a complete decision path in and out of this tool.

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?