Steer a running Codex turn

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

With no annotations, the description carries the full behavioral burden, yet it only discloses that the turn keeps running. It does not say what happens if no turn is active, whether instructions are queued or injected immediately, whether steering can fail, or what the call returns — all material for a mutation-style tool. The useful blocking behavior is documented only in the schema's wait_seconds field, not the description.

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?

A single tight sentence with no filler and the key constraint ('without stopping it') placed up front. It is arguably under-specified rather than over-long, but on conciseness and structure alone it is efficient.

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 3-parameter, no-annotation, no-output-schema tool, one sentence leaves significant gaps: failure modes, whether an active turn is required, and the return/progress behavior are all unaddressed. The description does not do enough to let an agent invoke this correctly in edge cases.

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 33%: only wait_seconds is documented, while prompt and thread_id (both required) have no description anywhere. The description adds no parameter meaning at all — it never mentions what the prompt should contain, whether it is additive to the original task, or how thread_id is obtained.

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 names a specific verb (add instructions / steer) and a specific target (the turn Codex is currently working on), which is clear enough to separate it from codex_run or codex_status. It stops short of naming the sibling it is most easily confused with (codex_respond, which presumably supplies the answer Codex is waiting for), so it is clear but not fully differentiated.

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?

'Without stopping it' implies the precondition that a turn is already running and that this is the non-disruptive alternative to codex_interrupt, but the agent must infer that. No explicit when-to-use, when-not-to-use, or named alternative (e.g., use codex_respond when Codex is blocked on a question) is given.

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