Wait for Codex progress

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

Annotations already declare readOnlyHint and idempotentHint, so behavioral disclosure of safety is covered. The description adds valuable context about long-polling semantics, terminal states, timeout behavior, and the eventCursor continuation mechanism, which goes beyond annotations.

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 two sentences, front-loaded with the action and outcome, and every phrase adds value. No wasted words.

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 simple polling tool, the description covers purpose, terminal conditions, timeout, and continuation with eventCursor. There is no output schema, but the description gives enough hint about the return value. It could mention what events contain or how to handle approval requests, but those may be covered by sibling tools like codex_resolve_approval.

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 50%: threadId and afterSequence are described, while maxEvents and timeoutMs are not. The description mentions 'timeout' and 'eventCursor', providing partial meaning for timeoutMs and afterSequence, but does not fully compensate for the undocumented parameters. Parameter names are mostly self-explanatory, but a clearer mapping would help.

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 the tool's function with a specific verb ('Long-poll') and a specific resource ('an active turn'), listing all terminal states: completes, fails, requests approval, interrupted, or timeout. This distinguishes it from siblings like codex_status (which likely polls status) and codex_read_thread (which reads a thread).

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 implies when to use this tool: after an active turn exists, to wait for completion or interruption, and to continue using the returned eventCursor. It does not explicitly name alternatives or exclusions, but the context is clear enough that an agent can infer it should be used instead of codex_status for blocking waits.

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