Start a direct command-line AI conversation and get a resumable thread ID to continue the session later.
Start a direct Codex CLI conversation and return a resumable thread ID.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | ||
| model | No | ||
| prompt | Yes | ||
| sandbox | No | read-only | |
| 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 must carry the behavioral burden. It usefully reveals that a thread ID is returned and that the conversation is resumable, but it says nothing about side effects, code execution, sandbox behavior, authentication, or failure modes. 'Direct CLI conversation' is too vague to understand what actually happens.
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 states the action and the most important result immediately, so every word earns its place.
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?
Despite having an output schema, the description leaves major gaps: it does not explain sandbox modes, what a 'direct conversation' means for execution, how to choose model or reasoning_effort, or how the returned thread ID should be used with codex_reply. For a tool with six parameters and a sibling, this is not enough context for reliable invocation.
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%, and the description names none of the six parameters. The schema only supplies field names, defaults, and an enum; without explanation, an agent cannot know the meaning of cwd, sandbox, web_search, or reasoning_effort. The description does nothing to compensate for this gap.
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 ('Start') with a clear resource ('Codex CLI conversation') and states the key result ('return a resumable thread ID'). This makes the tool's purpose unambiguous and distinguishes it from the sibling tool codex_reply, which presumably continues an existing 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 description clearly implies this tool is for initiating a conversation, especially by emphasizing the resumable thread ID. It does not explicitly mention when not to use it or name codex_reply as the alternative, but the context is clear enough for an agent to route initial calls here.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.