Continue a Codex session

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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description carries most of the burden. It usefully adds the context-retention/cost benefit of reusing an existing thread, but says nothing about side effects, permissions, or what state is modified on a follow-up turn.

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 tight sentences, no waste, with the thread_id mechanism and the cost rationale front-loaded. Every sentence 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?

Covers the core purpose and the key routing rationale for an 8-parameter mutation tool, and the thread_id link is clear. However, with no output schema and several undocumented parameters (auto_approve, timeout, working_dir), the description leaves notable behavioral gaps for a non-read-only 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 63%, with model, prompt, sandbox, thread_id and reasoning_effort documented and working_dir, auto_approve, timeout_seconds bare. The description reinforces the thread_id source and the context-reuse semantics, but adds nothing about sandbox, auto_approve, or timeout behavior. Baseline 3 fits the moderate 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?

States a specific verb and resource ('send a follow-up message to a previous delegation') and explicitly anchors it to the thread_id. It distinguishes itself from the sibling codex_delegate by naming it as the more expensive alternative.

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?

Clear when-to-use: continuing an existing delegation via thread_id, and it names codex_delegate as the alternative for re-sending context. It stops short of explicit when-not conditions (e.g., use codex_delegate for a fresh task), leaving that to inference.

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