codex_send

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the initial wait window (default 10s) and that incomplete work returns a snapshot plus recommended backoff for the next poll, but it omits side-effect and safety details such as session creation, permission implications, or what actions Codex may take.

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 three front-loaded sentences with no wasted text. It moves from purpose to configurable behavior to the asynchronous wait/return behavior in a logical order.

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?

Given nine parameters and no output schema, the description covers the core call pattern and the important partial-result behavior. The main gap is sibling routing: it does not explain how to continue with codex_poll after receiving a snapshot or when approval/cancellation tools are relevant.

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 100%, so every parameter is already documented structurally. The description only notes workspace directory, model, and permission mode, adding little meaning beyond the schema and leaving prompt, threadId, waitMs, effort, serviceTier, and safeTrashOnly to 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 clear verb and resource: send a prompt to Codex, either creating a new session or continuing an existing threadId. It also distinguishes the initial wait behavior from later polling, but it does not explicitly name or contrast sibling tools such as codex_poll or codex_cancel.

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?

Usage is implied: use this tool to send prompts and optionally continue an existing threadId, with a partial-result path for polling. However, the description does not explicitly state when to use it instead of codex_poll, codex_approve, or codex_cancel, nor does it describe exclusions or prerequisites.

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