codex_send_followup

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

The description adds significant behavioral context beyond annotations, such as invalidating prior verdict/obligation settlements and rejecting followups on completed turns. It also directs the user to inspect followup.steered or followup.delivery_failed events for delivery confirmation.

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, front-loading the primary action, and the conditional details are packed into a single sentence. It is not verbose, though the second sentence is dense with multiple conditions.

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?

The description provides adequate context for typical use, including success/failure detection through events, but does not detail error scenarios or what happens if the turn is not active beyond a brief mention, leaving some edge cases unspecified.

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?

The input schema has 0% coverage from the description, and the description does not explain the semantics of task_id or instruction. It implies the correction content, but does not explicitly map parameters to their roles, leaving the agent to infer.

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 'Send a correction immediately to the active Codex turn' with a specific verb and resource, and distinguishes itself by addressing conditions like awaiting_closure vs completed, which sets it apart from siblings like codex_start_task.

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 explicitly states when to use it: 'awaiting_closure accepts followups' and 'completed rejects followups (create a new task)', giving clear alternatives. It also notes the condition for starting a follow-up when no turn is active.

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