codex_send_message

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

With no annotations, the description carries full burden. It discloses the tool is a compatibility layer, returns immediately after turn/start, and that the first_message_timeout_seconds parameter is deprecated. It doesn't mention error conditions or side effects, but the mutation nature is implied.

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-loading the core purpose. It is efficient but the first sentence is somewhat jargon-heavy. There is no wasted text, though a bit more structure could improve readability.

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?

Despite having an output schema and 10 parameters, the description lacks explanation of many parameters (mode, approval_policy, sandbox, etc.) and does not describe the return value shape. It covers purpose and post-call polling but leaves significant gaps for proper agent use.

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 10% (one deprecated parameter). The description does not explain any other parameters like chat_id, mode, approval_policy, or sandbox. The agent receives no additional meaning beyond what the schema enum names provide.

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 it sends a new user message into an existing chat, using specific verbs and resources. It distinguishes from sibling tools by labeling itself a 'compatibility layer low-level write tool' and explicitly recommending codex_submit_task for durable tasks.

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 provides explicit guidance: it tells the agent when to use this tool (for low-level sending) and when to prefer an alternative (for durable long-running tasks). It also explains post-call behavior (poll codex_get_turn_status).

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