Skip to main content
Glama
AIops-tools

Nutanix AIops

by AIops-tools
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

undo_list

Read-only

List recorded, not-yet-applied undo tokens to review pending reversals before applying them. Each entry names the original tool, its inverse tool, and a note so you can pick an undoId.

Instructions

[READ] List recorded, not-yet-applied undo tokens (most recent first).

Each entry names the original tool, the inverse tool that ``undo_apply``
would run, and a human note. Use the ``undoId`` with ``undo_apply``.

``truncated`` is measured — one extra row is fetched — so a capped listing
announces itself instead of looking like the complete set.

Each entry carries ``effectVerified``. False means the original write
lost its response, so the change it reverses is PROBABLE, not confirmed —
check the live state before applying, and do not report the result as a
restore of a state that may never have been reached.

Args:
    limit: Max rows to return (default 50). Re-run with a higher limit when
        the result reports ``truncated: true``.
    target: Unused (undo state is host-local); accepted for CLI uniformity.

Input Schema

NameRequiredDescriptionDefault
limitNo
targetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only carry readOnlyHint, so the description does the heavy lifting: it explains the truncated flag is measured via an extra row fetch, and that effectVerified=false means the reversed change is only PROBABLE and needs live-state verification before reporting a restore. That is exactly the kind of non-obvious behavioral disclosure the annotation cannot convey.

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?

Front-loaded with the READ tag and the core action, then structured into entry contents, cautionary semantics, and an Args block. Slightly long — the effectVerified warning is repeated in two clauses — but every sentence carries operational value.

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, yet the description enumerates what each entry contains (original tool, inverse tool, human note) and explains the two salient fields, truncated and effectVerified. An agent has enough to call it and interpret the result correctly.

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

Parameters5/5

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

Schema coverage is 0%, so the description must compensate and does: limit is documented with its default (50) and the pagination behavior tied to truncated, and target is explicitly declared unused but accepted for CLI uniformity. With only two optional params, nothing is left ambiguous.

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+resource with scope: lists recorded, not-yet-applied undo tokens, most recent first. The distinction from the sibling undo_apply (which consumes these tokens) is explicit in the very next sentence.

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?

Gives a clear usage path ('Use the undoId with undo_apply') and a re-run condition when truncated is true. It does not, however, contrast against near-neighbors like snapshot_list or recovery_point_list, leaving the agent to infer why undo tokens rather than snapshots.

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