codex_start_chat

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

Discloses it is a write operation (low-level write tool), returns immediately after turn/start, and requires polling. Notes that first_message_timeout_seconds is deprecated and ignored. No annotations exist, so description carries full burden; it covers key behaviors.

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 essential information front-loaded. No fluff, but could be more structured for scanning.

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 11 parameters and availability of output schema, description covers high-level behavior and polling need but omits output details. Adequate but not comprehensive for a complex 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 description coverage is only 9%, but the description does not elaborate on parameters beyond mentioning project_id and message implicitly. Does not explain meaning of enums like sandbox or approval_policy, nor defaults. Fails to compensate for low schema 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?

Clearly states it starts a new Codex chat in a known project. Distinguishes from sibling codex_submit_task by calling itself a 'low-level write tool' and 'compatibility layer'.

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?

Explicitly advises preferring codex_submit_task for durable long-running tasks, and instructs to poll codex_get_turn_status for results. Provides clear when-to-use and when-not-to-use guidance.

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