Skip to main content
Glama

sylve_zfs_snapshot

Destructive

List, create, roll back, or delete ZFS snapshots and manage periodic snapshot jobs for cluster nodes or datasets.

Instructions

List, create, roll back, or delete ZFS snapshots, plus periodic snapshot jobs.

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": {
      "action": "<action>"
    },
    "name": "sylve_zfs_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoSnapshot name after @ (create).
nodeNoTarget cluster node hostname or UUID. Omit for cluster-wide.
actionYes
contextNoNamed login context from ~/.config/sylve/config.yaml.
datasetNoAlias for snapshot.
snapshotNoSnapshot name (dataset@snap) or GUID.
recursiveNo
destroy_more_recentNoRollback: destroy newer snapshots.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.7/5.0
Behavior2/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is known. The description adds nothing beyond that: it does not say which of the five actions are destructive (rollback/delete vs list), what rollback discards, or whether delete needs confirmation, despite being a single tool with mixed read and destructive actions.

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?

A single front-loaded sentence with zero padding. There is no bloat, but the terseness leaves content gaps rather than earning full marks for structure.

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

Completeness2/5

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

For an 8-parameter, five-action tool that mixes read and destructive operations, with no output schema and only hint-level annotations, the description is too thin. An agent cannot tell from the description which parameters each action requires or what a list/periodic_list returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 75% (below the 80% threshold) with 8 parameters, and the description contributes nothing about any of them. It only echoes the action vocabulary; the action-to-parameter mapping (dataset+name for create, snapshot for delete, recursive and destroy_more_recent only for rollback) is left entirely to inference.

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?

States specific verbs (list, create, roll back, delete) against a specific resource (ZFS snapshots, plus periodic snapshot jobs). An agent can distinguish it from sylve_zfs_pool / sylve_zfs_dataset, though the description does not explicitly rule out sylve_vm_snapshot or sylve_jail_snapshot.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The verb list roughly maps onto the action enum, but the description gives no when-to-use guidance, no prerequisites (permissions, context, node scoping), and never names the sibling snapshot tools it should be preferred over or deferred to.

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