Skip to main content
Glama

codex_delete

Destructive

Permanently delete an owned Codex conversation and its descendants by confirming the exact thread ID; the thread family must be idle, and local audit records remain.

Instructions

Permanently delete an owned native conversation and descendants. Requires the exact native thread_id in confirm_thread_id and an idle family. Local bridge audit records remain.

Input Schema

NameRequiredDescriptionDefault
task_idYesTask id
request_idNoKey for identical retries
operation_idNoAlias of request_id
confirm_thread_idYes

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and non-idempotency, but the description adds real substance beyond them: deletion cascades to descendants, the operation is permanent, the family must be idle, and local bridge audit records survive. It stops short of saying what error or state results when the idle requirement is unmet.

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?

Three short sentences, front-loaded with the irreversible action and its blast radius, followed by prerequisites and the audit-record caveat. No filler and nothing buried.

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?

For a destructive tool with an output schema available, the description covers permanence, cascade scope, prerequisites, and data-retention implications. The main remaining gap is failure behavior when the family is busy, which an agent preparing the call would benefit from.

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 75% and the description clarifies confirm_thread_id — that it must be the exact native thread_id and serves as a confirmation guard, which the schema leaves undocumented. It adds nothing about request_id/operation_id aliasing or task_id, which the schema already covers.

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 ('Permanently delete') and resource ('owned native conversation and descendants'), with the cascade scope made explicit. The word 'Permanently' implicitly separates it from the archive/compact siblings, but no sibling is named, so differentiation relies on the agent's inference.

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?

Preconditions are stated (exact native thread_id in confirm_thread_id, an idle family), which tells the agent when the call will succeed. There is no explicit guidance on choosing this over codex_archive or codex_compact, nor what to do when the family is not idle.

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