Skip to main content
Glama

jobd_list

Read-only

List jobs and per-state counts on the jobd broker to see what is queued, assigned, or running now, or filter by state, project, or finished_at window to find past runs and failed jobs.

Instructions

List jobs on the broker with per-state counts. Defaults to the active set (queued/assigned/running); filter by state (e.g. ['failed']), project, or a finished_at window (finished_after/finished_before) to find past runs. Each row is a compact summary: job_id, project, state, host, exit_code, queued_at, started_at, finished_at, duration_s — call jobd_status for a job's full record. Use to answer 'what is running / queued right now?', 'what failed overnight?', or to locate a job id you've lost.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "jobd_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax jobs returned (newest first; clamped to [1,200]). `counts` still covers every job matching the filters; a `truncated` field reports how many were cut.
stateNoStates to include — any of: queued, assigned, running, completed, failed, cancelled, preempted, orphaned, scheduling_timeout. Omit for the active set (queued/assigned/running); pass [] for all states.
projectNoRestrict to one project's jobs (the --project value used at submit).
finished_afterNoOnly jobs with finished_at at or after this: ISO-8601 (no offset = UTC) or relative (2h, 3d, 1w = that long ago). With a window and no state, every terminal state is included and counts cover the window exactly.
finished_beforeNoOnly jobs with finished_at before this (exclusive); same formats as finished_after.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.5.52
    • addedInput schema / properties / finished_after
      Added value: +{
      +  "description": "Only jobs with finished_at at or after this: ISO-8601 (no offset = UTC) or relative (2h, 3d, 1w = that long ago). With a window and no state, every terminal state is included and counts cover the window exactly.",
      +  "type": "string"
      +}
    • addedInput schema / properties / finished_before
      Added value: +{
      +  "description": "Only jobs with finished_at before this (exclusive); same formats as finished_after.",
      +  "type": "string"
      +}
  2. Changed2 schema fields changedv0.5.47
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / state / items / enum
      Added value: +[
      +  "queued",
      +  "assigned",
      +  "running",
      +  "completed",
      +  "failed",
      +  "cancelled",
      +  "preempted",
      +  "orphaned",
      +  "scheduling_timeout"
      +]
  3. Addedv0.5.36
  4. Removedv0.5.35
  5. Changed2 schema fields changedv0.5.12
    • changedInput schema / properties / limit / description
      Previous value: -"Advisory cap on returned jobs (the broker currently returns its default window)."New value: +"Max jobs returned (newest first; clamped to [1,200]). `counts` still covers every job matching the filters; a `truncated` field reports how many were cut."
    • changedInput schema / properties / state / description
      Previous value: -"States to include — any of: queued, assigned, running, completed, failed, cancelled, preempted, orphaned, scheduling_timeout. Currently only the first is forwarded to the broker (single state_filter)."New value: +"States to include — any of: queued, assigned, running, completed, failed, cancelled, preempted, orphaned, scheduling_timeout. Omit for the active set (queued/assigned/running); pass [] for all states."
  6. Changed3 schema fields changed
    • addedInput schema / properties / limit / description
      Added value: +"Advisory cap on returned jobs (the broker currently returns its default window)."
    • addedInput schema / properties / project / description
      Added value: +"Restrict to one project's jobs (the --project value used at submit)."
    • changedInput schema / properties / state / description
      Previous value: -"States to include. Currently only the first is forwarded to the broker (single state_filter)."New value: +"States to include — any of: queued, assigned, running, completed, failed, cancelled, preempted, orphaned, scheduling_timeout. Currently only the first is forwarded to the broker (single state_filter)."
  7. First observedv0.5.5

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds real context beyond them: the default state scope, that rows are compact summaries rather than full records, and which fields come back, plus the notable rule that a finished_at window without a state expands to all terminal states. It stops short of describing ordering beyond "newest first", but that lives in the schema.

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 scope and default are front-loaded, followed by filtering options, return shape, and use cases in a logical order with no filler sentences. The enumeration of returned fields is slightly list-heavy, but it earns its place by contrasting the compact row with jobd_status's full record.

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?

There is no output schema, and the description compensates by naming the returned fields and labeling the result as a compact summary, while pointing to jobd_status for the complete record. Combined with defaults, filter behavior, and intended queries, an agent has everything needed to call this correctly on the first attempt.

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 100%, so each parameter (limit, state, project, finished_after, finished_before) is already fully documented, including clamping, truncation counting, and relative time formats. The description only restates filtering at a high level and offers a bare example (['failed']); it adds little syntax or semantics the schema does not already carry. Baseline 3 applies.

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?

"List jobs on the broker with per-state counts" gives a specific verb, resource, and added value (counts), and the description immediately distinguishes itself from jobd_status ("call jobd_status for a job's full record"). An agent can tell this list/summary tool apart from the single-job lookup 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?

It states the default scope (active set: queued/assigned/running) and gives concrete selection scenarios: "what is running / queued right now?", "what failed overnight?", "locate a job id you've lost", each mapping to a specific filter. It also names the alternative for deeper inspection, so the routing decision is explicit rather than inferred.

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