Skip to main content
Glama

job_continue

Resume a blocked, failed, or finished job by sending a corrective hint in the original executor conversation, preserving prior context to avoid restarting work.

Instructions

Send a stopped job on with a hint of yours, in the same conversation of the executor.

For a job that ended blocked, stuck, checks_failed, out_of_steps or out_of_time, or a finished one that needs a correction. The executor keeps what it read and tried, so one sentence from you (the cause it missed, the file to look at, the approach to take) costs far less than a new task. The journal goes on: job_rollback still undoes the whole job. It also works after a restart of the server, since the conversation is saved at every step.

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>",
      "hint": "<hint>"
    },
    "name": "job_continue"
  }
}

Input Schema

NameRequiredDescriptionDefault
hintYes
job_idYes
extra_stepsNo
wait_secondsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.1

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 substantial work: it discloses that the executor retains what it read and tried, that the journal continues rather than restarting, that job_rollback still undoes the whole job, and that the resume survives a server restart because the conversation is persisted each step. It does not disclose that the call may block (wait_seconds) or that extra_steps expands the budget, both of which are behavioral facts an agent would want before invoking.

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?

The opening sentence is front-loaded with the core action and the executor-conversation constraint, and the remaining sentences each add a distinct fact (valid states, cost comparison, rollback relationship, restart durability). Some phrasing is more literary than necessary ('The journal goes on'), but nothing is clearly redundant.

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?

An output schema exists, so return values need not be explained, and the description covers the state machine and persistence story well for a mutating resume operation with zero annotation coverage. The gap is the two unmentioned numeric parameters plus the absence of any statement about blocking behavior or whether the call returns immediately versus waiting, which matters for an agent deciding how to invoke it.

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 description coverage is 0% across four parameters, so the description must compensate and only partly does. It gives real meaning to 'hint' by suggesting content ('the cause it missed, the file to look at, the approach to take') and implicitly to job_id, but extra_steps (default 15) and wait_seconds (default 240) are never mentioned anywhere, leaving half the parameters semantically opaque.

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?

The description gives a specific verb and resource ('send a stopped job on') and pins down the exact scope: it resumes the same executor conversation rather than starting fresh. Enumerating the terminal states (blocked, stuck, checks_failed, out_of_steps, out_of_time, finished-but-wrong) tells an agent precisely which jobs this applies to, which no sibling name alone conveys.

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?

It states when to reach for this tool (a job that stopped in one of the listed states, or a finished job needing correction) and contrasts the cost against 'a new task', effectively positioning it against a fresh delegation. It also names the sibling job_rollback as the tool for undoing the whole job, which is a genuine alternative. It stops short of stating explicit when-not conditions, such as when a new job is actually warranted.

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