Skip to main content
Glama

job_stop

Request that a running job or batch halt at its next safe point without interrupting an in-flight model call, then return a receipt that may still show running.

Instructions

Ask a running job or batch to stop at its next safe point. An in-flight model call is not interrupted: it can take up to TANDEM_TIMEOUT seconds. Returns the receipt, which may still show running.

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_id": "<job_id>"
    },
    "name": "job_stop"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYes
wait_secondsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.6.1

TDQS

A3.9/5.0
Behavior5/5

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

With no annotations, the description still discloses the important non-obvious behavior: stopping is requested rather than forced, an in-flight model call is not interrupted, that call may last up to TANDEM_TIMEOUT seconds, and the returned receipt may still report running. These details prevent an agent from assuming synchronous completion or immediate termination.

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?

Three compact sentences front-load the operation and then cover the two most important timing and result caveats. There is no filler or repetition, and each sentence contributes actionable information.

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

Completeness3/5

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

The description is sufficient for selecting the tool and making a basic call with the required job_id, while the output schema reduces the need for further return-value documentation. However, the unexplained optional wait_seconds parameter, undefined TANDEM_TIMEOUT reference, and absence of follow-up guidance leave meaningful gaps for correct invocation and interpretation.

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

Parameters2/5

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

Schema description coverage is 0%, and the description only indirectly clarifies that the identifier targets a running job or batch. It never explains wait_seconds, including whether it controls polling or blocking and how it relates to TANDEM_TIMEOUT, so it does not adequately compensate for the undocumented schema.

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?

The description uses a specific verb and resource: it asks a running job or batch to stop, and "at its next safe point" clarifies that this is a cooperative stop rather than an immediate kill. It does not explicitly contrast the tool with siblings such as job_continue or job_rollback.

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?

The running-job-or-batch scope and safe-point wording provide clear context for choosing a graceful stop request. There are no exclusions, prerequisites, or guidance about alternatives or how to monitor the job afterward.

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