codex_start

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

The description discloses that the sandbox is read-only and that permissions are determined by user startup configuration, not tool parameters. However, with no annotations provided, the description carries the burden; it doesn't mention what happens to the job after starting, how to check status, or any side effects beyond returning a jobId.

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 concise and front-loaded with the main action and return value. It includes important behavioral notes about read-only sandbox and permissions. Slightly dense but each sentence adds value.

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?

For a tool that starts a task, the description covers the core action, return value, model selection, and sandbox constraints. However, it lacks details about how to use the returned jobId, how to handle errors, or what happens if the thread doesn't exist. Given the sibling tools for status/cancel, an agent might need more guidance on the lifecycle.

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 mentions prompt, cwd, model, and threadId implicitly (new or existing thread), but doesn't explain the format or constraints of each parameter beyond what the schema already shows. It adds some context about model selection but not enough to fully compensate for the 0% coverage.

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 clearly states the tool starts a task in a new or existing Codex thread and immediately returns a jobId. It also mentions the model parameter for specifying the task model, which distinguishes it from sibling tools like codex_status or codex_cancel.

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 explains that it can be used in new or existing threads and that the model parameter can specify the model. It doesn't explicitly say when to use alternatives, but the context of starting a task is clear enough to differentiate from status/cancel/steer tools.

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