Skip to main content
Glama

codex_revert

Destructive

Remove a selected conversation turn and all later native history after explicit acknowledgement; does not revert files, and the local event audit remains.

Instructions

Remove a selected turn and all later native conversation history. DOES NOT revert files. Requires explicit acknowledgement; local event audit remains.

Input Schema

NameRequiredDescriptionDefault
task_idYesTask id
request_idNoKey for identical retries
operation_idNoAlias of request_id
before_turn_idYes
confirm_history_onlyYes

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds real value beyond them: it discloses the cascading delete ('all later native conversation history'), clarifies no file changes occur, and notes an audit trail persists ('local event audit remains'). It stops short of stating irreversibility or whether the operation can be undone.

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?

Three short, front-loaded sentences with no filler; the destructive scope comes first and the file-revert caveat immediately after. The telegraphic final clause ('local event audit remains') is slightly compressed but still lands.

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

Completeness3/5

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

For a destructive, cascading mutation the description covers the blast radius and audit behaviour well, and an output schema exists so return values need no explanation. However, the semantics of the required acknowledgement flag and the turn-boundary parameter remain unexplained, which is a notable gap for a data-loss operation.

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 60%, with task_id, request_id and operation_id documented in the schema. The description hints at the acknowledgement gate ('confirm_history_only') but doesn't explain that it must be set true, and it leaves 'before_turn_id' ambiguous — it says 'a selected turn' while the parameter name suggests an exclusive boundary.

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 a specific verb ('Remove') and resource ('a selected turn and all later native conversation history'), and explicitly bounds scope with 'DOES NOT revert files', which prevents confusion with any file-restoring operation. It does not name a sibling alternative, so it falls just short of a 5.

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

Usage Guidelines3/5

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

The description implies destructive history truncation and mentions a prerequisite ('Requires explicit acknowledgement'), but never says when to choose this over codex_delete, codex_compact, or codex_fork, nor when to avoid it. Usage has to be inferred from the word 'Remove' plus the destructive annotation.

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