Resume a prior Codex CLI conversation using its session ID and a new prompt, preserving context for continued problem-solving.
Continue a Codex CLI conversation using a prior thread ID.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | ||
| model | No | ||
| prompt | Yes | ||
| session_id | Yes | ||
| web_search | No | ||
| reasoning_effort | No |
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | ||
| result | Yes | ||
| metadata | No | ||
| sessionId | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility for behavior disclosure. It only states that the tool continues a conversation; it does not mention that Codex might execute commands, modify files, or take side-effecting actions, nor does it describe what happens after the reply is produced.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no filler. It is concise, though it borders on under-specification rather than being a model of efficient completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With six parameters, no annotations, and a sibling tool, one sentence is not enough. The agent is not told when to choose 'codex_reply' over 'codex', what the prompt should contain, or how optional parameters affect behavior. The output schema does not compensate for these invocation-level gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It only clarifies that 'session_id' refers to a prior thread ID. Required and optional parameters like 'prompt', 'cwd', 'model', 'web_search', and 'reasoning_effort' are left completely unexplained by the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Continue') and a clear resource ('a Codex CLI conversation') while adding the key mechanism ('using a prior thread ID'). This distinguishes it from the sibling 'codex' tool, which presumably starts a new conversation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'using a prior thread ID' gives a clear contextual signal for when this tool is appropriate: when there is an existing Codex session to continue. However, it does not explicitly state when not to use it or name the alternative 'codex' for starting new conversations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.