Send a prompt to a Codex thread

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

Annotations only declare the mutating/open-world/destructive profile; the description adds substantially more: a durable deliveryId is prepared before dispatch, ambiguous acknowledgements are marked unconfirmed, timeouts must be continued via wait_codex_reply rather than resent, and active-writer conflicts require codex_bridge_status. It also states explicit prohibitions (do not close the task, do not resend, do not ask the user to copy manually), which directly operationalizes the non-idempotent/destructive hints.

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?

Purpose and the same-task constraint are front-loaded in the first two sentences, with recovery procedures after. It is dense and roughly 180 words for a 9-parameter stateful tool, so a couple of sentences could be trimmed, but nearly every clause is actionable rather than filler.

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 mutating, non-idempotent, 9-parameter tool with no output schema and heavy delivery-state complexity, the description covers failure modes, timeout continuation, acknowledgement ambiguity, and recovery paths. An agent has everything it needs to invoke and recover correctly.

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 100%, so the baseline is 3 and the schema already documents threadId, cwd, prompt, timeout, and release semantics. The description adds only marginal parameter-level meaning (e.g., the cwd project check, the threadId discovery hint, the deliveryId that feeds wait_codex_reply) and is silent on name, model, effort, and openInApp.

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 first sentence states a specific verb and resource ('Send a prompt as a new user turn inside an existing Codex thread and wait for Codex to answer'). It distinguishes itself from siblings like start_codex_thread and delegate_to_codex by scoping to an *existing* thread. An agent can select it without opening any schema.

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 gives explicit when-to-use ('same unfinished task, including follow-up fixes, clarifications, or results') and when-not ('independent new work belongs in a new conversation'). It also names concrete alternatives for adjacent needs: list_codex_threads for discovery, wait_codex_reply for timeouts, codex_bridge_status for legacy writer problems.

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