codex_message

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

With no annotations, the description carries the burden of behavioral disclosure, and it does reveal meaningful behavior: it can act on a running turn or start a new one when idle, and it can error due to a race with turn completion. It provides actionable retry guidance, though it does not say what the success response looks like or whether the call blocks until the turn finishes.

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 sentences with no filler. The primary action is stated first, followed by the idle-thread behavior and the race-condition warning, all in an efficient, scannable structure.

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 core semantics and a key error condition are covered, but there is no output schema and no annotation to fill gaps about return values or lifecycle expectations. An agent would benefit from knowing what a successful response contains and how threadId relates to codex_start or codex_status, so the context is adequate but not comprehensive.

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 0%, so the description should compensate, but it only lightly does. 'Same thread' gives context to threadId, and 'send direction' hints at the message parameter's role. The parameter names and types are fairly self-explanatory, but the description does not clarify message content format, length expectations beyond schema, or how threadId should be 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 clearly states that the tool sends direction to a running Codex turn or starts a new turn in the same thread when idle. The action and target resource are identifiable, and the idle/running distinction adds precision, though it does not explicitly differentiate this tool from siblings like codex_start or codex_resume.

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 gives clear usage context: use it to direct a running turn, or to start another turn in the same idle thread. It also warns about a race with turn completion and advises inspecting status before retrying. It stops short of naming alternatives explicitly or saying when not to use this tool.

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