Skip to main content
Glama
Sign In
sysknife

sysknife

by lacs-project
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

sysknife_execute

Execute exact steps from a plan output. Each step requires a one-time approval receipt from the CLI confirmation command.

Instructions

Execute exact steps produced by sysknife_plan. Every step requires a one-time receipt from an explicit sysknife approve <transaction-id> CLI confirmation; MCP cannot approve its own mutations.

Input Schema

NameRequiredDescriptionDefault
stepsYesSteps to execute — take the `steps` array from `sysknife_plan` output.

Output Schema

NameRequiredDescriptionDefault
stepsYesResults for each attempted step, in order, including an interrupted step.
needs_rebootYesTrue if any step requires a reboot to take effect.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.27.1
    • changedOutput schema / $defs / StepResult / properties / action_name / description
      Previous value: -"Action that was executed."New value: +"Action whose execution was attempted."
    • changedOutput schema / $defs / StepResult / properties / needs_reboot / description
      Previous value: -"Whether this step requires a reboot to take effect."New value: +"Whether the daemon confirmed this step requires a reboot to take effect."
    • changedOutput schema / $defs / StepResult / properties / rollback_ref / description
      Previous value: -"Identifier of the rollback the daemon performed after a failure, when\none happened — e.g. the restored file or the previous deployment.\n`null` when the step succeeded or when nothing was rolled back."New value: +"Identifier of the rollback the daemon performed after a failure, when\none happened — e.g. the restored file or the previous deployment.\n`null` when no rollback was reported, including an unknown outcome."
    • changedOutput schema / $defs / StepResult / properties / status / description
      Previous value: -"Final status: `\"succeeded\"`, `\"failed\"`, `\"needs_reboot\"`, etc."New value: +"Final status, or `\"unknown\"` when the final daemon reply was lost."
    • changedOutput schema / $defs / StepResult / properties / warnings / description
      Previous value: -"Warnings emitted by the daemon for this step."New value: +"Daemon warnings, or a recovery warning when the outcome is unknown."
    • changedOutput schema / properties / steps / description
      Previous value: -"Results for each executed step, in order."New value: +"Results for each attempted step, in order, including an interrupted step."
  2. Changed1 schema field changedv0.1.5
    • addedOutput schema / $defs / StepResult / properties / rollback_ref
      Added value: +{
+  "description": "Identifier of the rollback the daemon performed after a failure, when\none happened — e.g. the restored file or the previous deployment.\n`null` when the step succeeded or when nothing was rolled back.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
  3. Addedv0.1.2

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden, and it delivers the single most important behavioral fact: MCP cannot approve its own mutations and a one-time CLI receipt is mandatory. It stops short of describing execution atomicity, partial-failure behavior, or side effects, which remain gaps.

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?

Two tight sentences: the action is front-loaded and the gating constraint follows immediately. Nothing is redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and the description covers the critical approval workflow and the plan-to-execute dependency. Missing only failure/partial-execution semantics for what is inherently a mutating tool.

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 both the steps array and StepToExecute fields are documented in-schema, so the baseline of 3 applies. The description reinforces the approval_receipt requirement but adds no new semantics about step ordering or passthrough behavior beyond what the schema already states.

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?

States a specific verb (Execute) and resource (exact steps produced by sysknife_plan), and explicitly ties the tool to the sibling planner so an agent can distinguish it from the read-only collector tools. The scope — executing plan output, not inspecting state — 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?

Clear prerequisite chain: steps must come from sysknife_plan and each requires a CLI approval receipt before execution. It does not explicitly name 'do not call without a prior plan' or cover alternatives, but the sequencing requirement is strong enough to route the agent correctly.

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