codex_start

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals important traits: full filesystem/network access, no approval prompts, and immediate return of the threadId after acceptance. It does not detail asynchronous execution or post-start behavior, but the disclosed runtime privileges are highly relevant and go well beyond the tool name.

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?

Two sentences with no filler. The core action and return value are front-loaded, and the second sentence adds the essential behavioral warning about permissions and the expected input strategy. Every clause 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?

Given no annotations, an output schema, and only three parameters, the description covers the key information needed to call the tool correctly: required inputs, optional model, return value, and significant runtime behavior. It could mention how to interact with the returned threadId via sibling tools, but that is not necessary for a correct first call.

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 maps cwd to 'absolute working directory' and prompt to 'complete task context', which adds real meaning over the raw schema. It also explicitly notes that model is optional. It does not enumerate model choices, but the sibling tool codex_models likely covers that.

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 and resource: 'Start a live Codex agent' and states it returns a threadId after acceptance. This clearly distinguishes the tool from siblings like codex_message, codex_stop, and codex_status, which operate on an already-started agent.

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 gives clear context for when to use the tool: to start a live Codex agent. It also instructs the caller to supply an absolute working directory and complete task context, and notes that model is optional. It does not explicitly list alternatives or when-not-to-use, but the verb 'start' and sibling names make the intended usage fairly clear.

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