Hermes Micro-Agent

Cancel a pending job

cancel_job

DestructiveIdempotent

Cancel a job still waiting for payment.

Free to call, no authentication. Only pending_payment jobs can be cancelled; a paid, done, failed, or refunded job is untouched and the response says why.

Behavior: marks the job cancelled. No funds move - no payment was taken. Cancelling twice is safe.

Parameters: an unknown key returns found=false.

When to use: when a job is stuck unpaid. For a paid job use refund_job.

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": "cancel_job"
  }
}

Input Schema

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

Output Schema

Name	Required	Description
`found`	Yes	false when no job exists with that key
`reason`	No
`job_key`	No
`cancelled`	Yes	true when the job was still pending_payment

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations: it clarifies that destructiveHint actually means only a status mark with no funds moving, that no payment was taken, that cancelling twice is safe, and that an out-of-state job returns a response explaining why. It also discloses the operational profile (free, no auth), which no annotation covers.

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?

Purpose is front-loaded and the labeled sections (Behavior, Parameters, When to use) make it scannable with no filler sentences. The 'Parameters' label is slightly misused since that line actually describes a return value, and the hard line wraps fragment sentences.

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 mutation with an output schema, the description covers everything an agent needs: precondition, state change, safety on retry, and failure signalling. The only return detail it gives ('the response says why') is a helpful pointer, not a substitute for the output schema.

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% with a single well-documented job_key, so the baseline is 3. The description adds only one behavioral note — an unknown key returns found=false rather than erroring — which is useful for handling bad input but is more output behavior than parameter semantics.

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 with an explicit scope: 'Cancel a job still waiting for payment.' The scope word 'pending_payment' distinguishes it immediately from refund_job, so an agent can route without opening either 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?

Gives a positive trigger ('when a job is stuck unpaid'), an exclusion ('a paid, done, failed, or refunded job is untouched'), and names the correct sibling for the other case ('For a paid job use `refund_job`'). Nothing about selection is left to inference.

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?