Skip to main content
Glama
AIops-tools

fabric-aiops

by AIops-tools
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

undo_list

Read-only

List not-yet-applied undo tokens, newest first, to choose an undoId for rollback and check effectVerified before applying.

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``.

One extra row is fetched so ``truncated`` is **measured**, not guessed from
the returned count happening to equal the limit — a capped list that cannot
say "there is more" invites a weak model to report it as the whole story.

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).
    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

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description adds substantial context beyond that: `truncated` is measured (an extra row is fetched), `effectVerified` flags where the original write lost its response so the reversal is PROBABLE not confirmed, and `target` is accepted but unused. That is genuinely useful behavioral guidance, though it doubles as design rationale rather than pure operator context.

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 core purpose, then the truncated/effectVerified caveats, then a compact Args block. Mostly tight, though the 'measured, not guessed' justification paragraph runs longer than strictly needed for an agent to act on.

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?

No output schema exists, and the description compensates by naming the return fields ('original tool, the inverse tool, a human note', `undoId`, `effectVerified`, `truncated`) and their semantics. For a zero-required-param read tool this is complete enough to call 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?

Schema coverage is 0%, so the description must carry both params — and it does: `limit` ('max rows, default 50') and `target` ('Unused... accepted for CLI uniformity'), the latter saving the agent from trying to use it. Defaults were already in the schema, so it is not fully additive, but the gap is well covered.

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?

Specific verb+resource: 'List recorded, not-yet-applied undo tokens (most recent first)'. The [READ] tag and 'not-yet-applied' scoping distinguish it clearly from the sibling undo_apply, which it explicitly references. An agent can tell the two apart without opening either schema.

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?

States the follow-on path: 'Use the `undoId` with `undo_apply`', routing the agent to the sibling. It also gives an important conditional: if `effectVerified` is False, check live state before applying. It stops short of explicit when-not-to-use-this (e.g., use undo_apply instead when you already have a token), but context is clear.

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