codex_start

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

With no annotations, the description carries the full behavioral burden and does well: it discloses that Codex runs with full filesystem/network access and no approval prompts (a significant risk disclosure) and that it returns asynchronously right after acceptance. It omits auth requirements, rate limits, and failure modes, which keeps it from a 5.

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?

Three sentences, front-loaded with purpose and the return value, then the risk disclosure, then the parameter guidance. No filler or repetition.

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?

There is no output schema, and the description names the returned threadId, which is the key output fact. It does not explain what to do with that threadId (poll codex_status/events), a minor gap for an async start tool.

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 coverage is 0%, so the description must compensate, and it does: cwd is explained as an absolute working directory, prompt as the complete task context, and model/serviceTier are flagged optional with a concrete example ('fast'). Format details such as the prompt length cap are left to the schema.

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?

States a specific verb and resource ('Start a live Codex agent') and names the immediate return value (threadId). It is clearly distinguishable from codex_stop/codex_resume in spirit, but it never explicitly contrasts itself with those siblings, so it stops short of a 5.

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?

It tells the agent to supply an absolute working directory and complete task context, which is usage-adjacent guidance, but there is no when-to-use/when-not-to-use statement and no routing to codex_resume for existing threads or codex_status/codex_events for monitoring. Usage is implied rather than stated.

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