Skip to main content
Glama
musharna

jobd

by musharna
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

jobd_submit

Submit a shell command to the job broker for queued execution on a capable worker. Run asynchronously by default, or block until completion by setting wait=true.

Instructions

Submit a job to the jobd broker. Default async; pass wait=true to block up to wait_timeout_s (server clamps to 270).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdYesAbsolute path; broker validates against worker mount_roots.
gpuNoPin to GPU-capable worker.
hostNoHost alias pin (laptop, desktop-vm).
waitNoSync mode: block until terminal or timeout. For an array submit (count/sweep), waits on every member under one shared deadline and returns an aggregate {array_id, count, job_ids, states, all_completed, members:[{job_id, state, exit_code}]}.
extraNoEscape hatch: idempotent (bool), depends_on (int[]), depends_on_any_exit (bool), priority (int delta), max_wall_s (int), idle_timeout_s (int), scheduling_timeout_s (int 1..604800 — give up and terminate the job as 'scheduling_timeout' if it is still QUEUED after N seconds; omit to wait indefinitely for a capable worker), checkpoint_grace_s (int 1..300), vram_gb (float — explicit GPU VRAM the job needs at dispatch; falls back to cuda-Ngb tier-tag max, then to 2 GB floor for --gpu jobs), count (int 1..1000 — submit a job array of N members, with `{i}` in the command replaced by the 0-based index; response is {array_id, count, job_ids, warnings} instead of a single job), sweep (list of {key, values[]} — parameter-sweep axes; broker fans out the cartesian product, substituting `{key}` per member plus `{i}`; mutually exclusive with count; product capped at 1000), profile (str), env (dict), preemptible (bool), session_id (str), arch (str — pin to a worker CPU arch), os (str — pin to a worker OS).
needsNoTool tags (R, python3, cuda).
commandYesShell command run by the worker shell.
dry_runNoPreview mode: run full validation + routing decision (profile, project defaults, cwd, depends_on, preflight, gpu_contention) and return the would-be plan WITHOUT queueing. Response has state='dry-run', would_route_to (list[host]), would_use_worker (host or null), validation (resolved fields + warnings). Per dry-run convention 2026-05-18.
projectYesScheduling identity. A registered projects.yaml name (matched case- and -/_-insensitively) prices at its priority; an unregistered name is priced by the project whose roots: contain cwd, else by _default. The result's project_label carries the name as typed when the two differ.
wait_timeout_sNoSeconds; permissive — server clamps to 270.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.44
    • changedInput schema / properties / project / description
      Previous value: -"Priority lookup key; falls back to _default."New value: +"Scheduling identity. A registered projects.yaml name (matched case- and -/_-insensitively) prices at its priority; an unregistered name is priced by the project whose roots: contain cwd, else by _default. The result's project_label carries the name as typed when the two differ."
  2. Addedv0.5.35
  3. Removedv0.5.34
  4. Changed1 schema field changedv0.5.26
    • changedInput schema / properties / extra / description
      Previous value: -"Escape hatch: idempotent (bool), depends_on (int[]), depends_on_any_exit (bool), priority (int delta), max_wall_s (int), idle_timeout_s (int), checkpoint_grace_s (int 1..300), vram_gb (float — explicit GPU VRAM the job needs at dispatch; falls back to cuda-Ngb tier-tag max, then to 2 GB floor for --gpu jobs), count (int 1..1000 — submit a job array of N members, with `{i}` in the command replaced by the 0-based index; response is {array_id, count, job_ids, warnings} instead of a single job), sweep (list of {key, values[]} — parameter-sweep axes; broker fans out the cartesian product, substituting `{key}` per member plus `{i}`; mutually exclusive with count; product capped at 1000), profile (str), env (dict), preemptible (bool)."New value: +"Escape hatch: idempotent (bool), depends_on (int[]), depends_on_any_exit (bool), priority (int delta), max_wall_s (int), idle_timeout_s (int), scheduling_timeout_s (int 1..604800 — give up and terminate the job as 'scheduling_timeout' if it is still QUEUED after N seconds; omit to wait indefinitely for a capable worker), checkpoint_grace_s (int 1..300), vram_gb (float — explicit GPU VRAM the job needs at dispatch; falls back to cuda-Ngb tier-tag max, then to 2 GB floor for --gpu jobs), count (int 1..1000 — submit a job array of N members, with `{i}` in the command replaced by the 0-based index; response is {array_id, count, job_ids, warnings} instead of a single job), sweep (list of {key, values[]} — parameter-sweep axes; broker fans out the cartesian product, substituting `{key}` per member plus `{i}`; mutually exclusive with count; product capped at 1000), profile (str), env (dict), preemptible (bool), session_id (str), arch (str — pin to a worker CPU arch), os (str — pin to a worker OS)."
  5. First observedv0.5.5

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the burden. It discloses important behavioral details: default async, wait blocking until timeout, server clamping to 270, array/sweep fan-out, dry_run preview behavior, and scheduling_timeout termination semantics. It does not cover all side effects (e.g., what happens on cancellation or resource cleanup), but for a submission tool this is strong behavioral disclosure.

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 core description is a tight two-sentence opener that states the default and the wait behavior. The parameter descriptions are long, especially extra, but they are dense with necessary detail for a complex submission API. Some redundancy exists (wait_timeout_s appears in the description and the schema), but the upfront structure is effective.

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?

Despite having no output schema and no annotations, the description covers the key behaviors an agent needs: async/sync modes, clause, dry-run, array/sweep aggregates, and the escape-hatch semantics. For a 10-parameter tool with nested object and array options, this is unusually complete. The only missing piece is the single-job response shape, but the description covers enough to call it correctly.

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?

Schema description coverage is 100%, so baseline is 3. The description adds meaningful behavior beyond the schema: wait=true is explained as sync mode with an aggregate response shape, dry_run details are expanded to mention full validation and routing decision, and the extra object is contextualized as an escape hatch with specific key meanings. It still defers most parameter detail to the schema, but the added context is valuable, especially for wait, dry_run, and extra.

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 starts with a clear verb+resource ('Submit a job to the jobd broker'), immediately distinguishing it from sibling tools like jobd_cancel, jobd_logs, or jobd_status. It also states the default behavior (async) and the wait option, so an agent knows both what the tool does and its primary mode distinction.

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 description explains when to use wait=true and mentions the server clamp, giving concrete usage context. It does not explicitly name sibling alternatives or state when not to use this tool, but the operation is so central to the sibling set that the default guidance is sufficient. The array and sweep options also add clear usage context for advanced submissions.

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

Deploy Server

Other Tools