Skip to main content
Glama

Continue Codex session

codex_continue

Resume an existing Codex session in a workspace to send a follow-up prompt, keeping its original sandbox, model, and thread context. Pass the same workspace so Codex still sees the repo.

Instructions

Continue the Codex session: resumes the thread rooted at this workspace (codex exec resume), so pass the same workspace= as the ask (without it the sub-agent sees no repo). It resumes the session the last codex_ask there started, else the newest on-disk session for that directory. The session keeps its original sandbox and model. Autonomous agent: trusted prompts only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "codex_continue"
  }
}

Input Schema

NameRequiredDescriptionDefault
watchNoIf true, open the live "watch" view streaming codex's steps as it works (same viewer as codex_ask). Default false.
promptYesFollow-up message for the existing session.
timeout_sNoMax seconds to wait for codex to complete. Default 180.
workspaceNoWorking root used by the prior session. Defaults to the server cwd.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.12.2

TDQS

A4.7/5.0
Behavior5/5

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

Adds real behavior beyond the annotations: session selection falls back to the newest on-disk session for that directory, the session retains its original sandbox and model, and 'trusted prompts only' flags a security posture for an autonomous agent. None of that is derivable from readOnlyHint=false, openWorldHint=true, idempotentHint=false.

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?

Front-loaded with the verb and resource, then the workspace prerequisite, then fallback and sandbox semantics in a few tight sentences. No sentence is filler and the ordering matches how an agent needs the information.

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?

An output schema exists, so return values need not be described, and the description covers the remaining ambiguities of a session-resume tool: which session is resumed, what workspace to pass, and what carries over. Nothing needed to invoke it correctly is missing.

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 100%, so baseline is 3, but the description goes further: it explains why workspace must match the prior ask and what breaks without it, adding meaning beyond the schema's 'Defaults to the server cwd.' The other parameters (prompt, watch, timeout_s) are left to the schema.

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 and resource ('Continue the Codex session', 'resumes the thread rooted at this workspace') and ties it directly to the sibling codex_ask that starts the thread, so an agent can tell continue from ask without opening a 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?

Gives a concrete prerequisite ('pass the same workspace=<project dir> as the ask') and explains the consequence of omitting it ('the sub-agent sees no repo'). It implies the pairing with codex_ask rather than stating an explicit when-not rule, which keeps it just below a 5.

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