Send a prompt to a Codex thread

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

Annotations declare destructiveHint=true and readOnlyHint=false. The description adds meaningful behavioral context: it waits for Codex to answer, preserves thread history/cwd/model, warns against closing the task, and explains the timeout behavior. It also details desktop delivery constraints and repair steps. This goes beyond the annotations without contradiction.

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 moderately long but every sentence contributes: it states the action, gives usage guidance, lists constraints, and provides an error-handling path. It is front-loaded with the primary purpose and structured logically. It is not overly verbose, though it could be trimmed slightly without losing meaning.

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 tool with 9 parameters and no output schema, the description covers usage, constraints, and error handling. It does not explicitly describe the return format, but the phrase 'wait for Codex to answer' implies the answer is returned. The description also addresses edge cases like desktop delivery and timeouts. The only minor gap is the lack of an explicit return type, but this is likely inferred.

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 100%, so the baseline is 3. The description adds value by explaining that threadId comes from list_codex_threads, that cwd and model are overrides for the thread's defaults (since the thread keeps its own), and that timeoutSec is capped at 40s on Desktop with the task continuing. It does not explain releaseAfterTurn, but the parameter name and schema description cover it. Overall, it enhances parameter understanding beyond the schema.

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 states a specific action ('send a prompt as a new user turn inside an existing Codex thread'), identifies the resource (prompt) and the destination (existing thread), and implicitly distinguishes from siblings by emphasizing 'existing' and pointing to list_codex_threads for threadId discovery. It is clear and unambiguous.

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 explicitly instructs to use list_codex_threads when threadId is unknown, specifies the condition for Desktop-owned tasks (must use native delivery), and gives a fallback action when legacy delivery reports an active writer (inspect codex_bridge_status). This provides clear when-to-use and when-not-to-use guidance with alternatives.

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