dbx-mcp

Manage jobs

manage_jobs

Destructive

Create, inspect, update, reset, delete, or trigger Databricks Lakeflow Jobs with confirmation safeguards for destructive actions.

Instructions

Create, inspect, change, delete and trigger Databricks Lakeflow Jobs.

create: spec = JobSettings fields (name, tasks, job_clusters, environments, schedule, trigger, continuous, parameters, email_notifications, webhook_notifications, tags, queue, max_concurrent_runs, timeout_seconds, git_source, run_as, access_control_list, ...). Each task needs task_key and one task type (notebook_task, spark_python_task, python_wheel_task, sql_task, pipeline_task, run_job_task, ...) plus compute (existing_cluster_id, job_cluster_key, new_cluster, or environment_key for serverless).
get (job_id), list (name filter, paginated).
update (job_id, spec and/or fields_to_remove): partial; top-level fields in spec replace existing ones, tasks/job_clusters are merged by key.
reset (job_id, spec): full overwrite of all settings (DESTRUCTIVE, needs confirm).
delete (job_id): DESTRUCTIVE, needs confirm.
run_now (job_id, spec: job_parameters, notebook_params, python_params, only, queue, performance_target, idempotency_token, ...): returns the run_id immediately (status 'pending'); wait=true polls (bounded). Specs setting run_as/access_control_list are additionally SECURITY_SENSITIVE (confirm required).

Safety classification: depends on input (DESTRUCTIVE, EXECUTION, READ_ONLY, SECURITY_SENSITIVE, WRITE).

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	list only: exact job name filter (server-side).
`spec`	No	Request body fields for create/update, using the Databricks REST API field names (snake_case). Unknown fields are rejected.
`wait`	No	run_now only: poll until the run finishes (bounded).
`action`	Yes	create: new job from spec; get: full job definition; list: jobs (optional name filter); update: partial change (spec = fields to set, fields_to_remove); reset: replace ALL settings with spec; delete: delete the job; run_now: trigger a run (spec = run parameters).
`job_id`	No	Job id (get/update/reset/delete/run_now).
`confirm`	No	Set to true ONLY after the user has reviewed the plan returned by a previous call with status 'confirmation_required'. Required for destructive/security-sensitive actions.
`dry_run`	No	If true, validate and return the planned change without executing it.
`page_size`	No	Max items to return (server caps this).
`page_token`	No	next_page_token from a previous response.
`timeout_seconds`	No	run_now with wait=true: max seconds to wait (capped by server).
`fields_to_remove`	No	update only: top-level settings to remove, or 'tasks/<task_key>' / 'job_clusters/<key>'.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No
`page`	No
`plan`	No
`tool`	Yes
`action`	No
`safety`	No
`status`	No		success
`summary`	Yes
`warnings`	No
`next_steps`	No	Suggested follow-up calls.
`request_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 3, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true, readOnlyHint=false, openWorldHint=true, but the description adds rich operational detail: which actions require confirm, the SECURITY_SENSITIVE confirmation for run_as/access_control_list, partial vs full overwrite semantics, and the wait polling behavior for run_now. This goes well beyond structured data.

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 description is front-loaded with a clear purpose statement, then uses bullet points to organize action-specific details. It is somewhat long because it enumerates many spec fields, but the structure is efficient and no sentence is wasted.

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?

Given the tool's complexity (11 parameters, 7 actions), the description covers all actions, safety confirmations, dry_run, and run_now return behavior. With an output schema present, return values need not be explained, so the definition is complete for an agent 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?

The schema has 100% description coverage, so the baseline is 3. However, the description adds significant meaning about the 'spec' object expected fields, task requirements, and update merge semantics, which are not fully captured in the schema's high-level parameter descriptions.

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 opens with a specific verb list and resource ('Create, inspect, change, delete and trigger Databricks Lakeflow Jobs'), then enumerates every supported action. It does not explicitly name alternative tools for run management, but the purpose is unambiguous.

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 action descriptions give clear context for when to use each mode (e.g., create vs update vs reset), and the safety notes explain prerequisites like confirm and dry_run. No explicit when-not-to-use guidance or sibling alternatives are named, so it stops short of the top rubric.

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

Deploy Server