Skip to main content
Glama

sync_jobs

Declaratively align an account’s cron jobs with a specified set: preview deletions and changes via dry-run diff, then apply after confirmation.

Instructions

Make the account's jobs match a declared set (declarative, like norc gitops). Jobs not listed are DELETED. Defaults to a dry run that only returns the diff; set apply=true to execute it. Always show the user the dry-run diff, especially the deletes, and get their confirmation before applying. Requires the gitops sync feature on the account.

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": {
      "jobs": "<jobs>"
    },
    "name": "sync_jobs"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobsYesThe complete desired job set across all machines
applyNoExecute the diff. Default false (dry run).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.3

TDQS

A4.3/5.0
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 well: it discloses that unlisted jobs are destroyed, that the default is a safe dry-run returning only a diff, and that a feature flag is required. It does not say whether deletions are recoverable, how invalid cron entries are handled, or what the diff payload looks like beyond being 'the diff'.

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?

Four short sentences, front-loaded with the destructive replace semantics before the safety workflow. Every sentence adds a distinct constraint (declarative model, deletion, dry-run default, feature requirement) with no filler.

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 still tells the agent what comes back (a diff) and how to sequence the call (dry run, show user, confirm, then apply). For a destructive bulk-reconcile tool with no annotations, that covers exactly what an agent needs to call it safely.

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 coverage is 100% and the schema already documents both parameters, including that apply defaults to false (dry run) and that jobs is the complete desired set. The description restates both points and emphasizes the destructive replace semantics, which is useful framing but largely redundant with the schema, so the 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?

The description states a precise verb and resource ('make the account's jobs match a declared set'), names the model (declarative, like `norc gitops`), and states the consequence ('Jobs not listed are DELETED'). That immediately separates it from the sibling CRUD tools like create_job/update_job/delete_job without needing to name them.

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 gives concrete operational guidance: default dry run, set apply=true to execute, always show the user the diff and get confirmation, and the account must have the gitops sync feature. What's missing is explicit routing against siblings (e.g., 'for a single job, use update_job instead'), so the agent must infer that this tool is for whole-set reconciliation.

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