Skip to main content
Glama

codex_resume

Destructive

Reconcile native history and execution intent after a reconnect without replaying prompts or commands, then inspect codex_history before a follow-up.

Instructions

Reconcile native history and execution intent after reconnect. No prompt or command replay. Inspect codex_history before a follow-up.

Input Schema

NameRequiredDescriptionDefault
task_idYesTask id
request_idNoKey for identical retries
operation_idNoAlias of request_id

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false, and openWorldHint=true, so the safety profile is covered. The description does add real behavioral information — 'No prompt or command replay' tells the agent no work is re-executed — but it never explains what state gets destroyed or how 'reconcile' mutates history, which is the critical gap for a destructive tool.

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 tight sentences with no filler; the 'no replay' constraint and the follow-up workflow instruction are both front-loaded. The opening sentence is the weakest because its abstraction, not its length, is the problem.

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?

An output schema exists, so return values need not be explained, and the annotations carry the mutability profile. However, for a destructive, non-idempotent resume operation, the description should say what gets reconciled or lost and whether follow-up requires a specific identifier — the agent is left to infer that from context.

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 description coverage is 100%, so all three parameters (task_id, request_id, operation_id) are documented in the schema and baseline is 3. The description adds nothing about the retry-key semantics, and notably does not reconcile the apparent tension between request_id ('Key for identical retries') and idempotentHint=false.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the abstract verb 'Reconcile's against 'native history and execution intent', never plainly stating that this resumes a task/session after a reconnect. 'Resume' appears only in the tool name, and the distinction from siblings like codex_get or codex_status is left implicit, though the reference to codex_history gives some anchoring.

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?

It gives a clear trigger ('after reconnect', 'after... a follow-up') and names a prerequisite sibling ('Inspect codex_history before a follow-up'). It does not say when not to use this versus codex_history, codex_get, or codex_status, so the routing guidance is implied rather than explicit.

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