run_codex

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It transparently explains async non-blocking behavior, automatic retries with exponential backoff on 429/rate-limit/timeout, session resumption semantics, and that the new session id is captured and returned. It also notes max_retries=0 to disable retries. This is substantial context, though it does not disclose return value structure or file-modification side effects.

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 tight and efficient, with each clause carrying distinct information: purpose, async nature, session resumption, and retry behavior. It front-loads the action and then layers key details without redundancy. No filler or unnecessary text.

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 13 parameters, no annotations, and no output schema, the description could offer more on how task tracking works (e.g., role of task_id, how to check status) and what the return payload contains. It covers the most important behavioral aspects (async, retries, session resumption) well, but leaves workflow integration details to sibling tools and some parameters ambiguous.

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 46%, so the description must compensate. It adds meaningful semantics for session_id (resume prior session, new id returned) and max_retries (default 2 retries, 3 total attempts, 0 disables), and indirectly clarifies retry_base_ms/retry_max_ms by describing exponential backoff. However, several parameters (prompt, task_id, workdir, model, auto, timeout_sec) are not explained in the description, leaving gaps that the low schema coverage cannot fill.

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 verb and resource: 'Async call Codex CLI (codex exec) to run a task.' It further scopes the tool to 'batch codegen/patches' and emphasizes 'Non-blocking', which clearly distinguishes it from sibling tools like run_claude, run_qwen, and run_dsh. An agent can tell exactly what this tool does and when it is the right choice.

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 says 'For batch codegen/patches' and highlights 'Non-blocking' and 'Async', which gives clear context for when to use this tool. However, it does not explicitly name alternative tools or state when not to use it, so it lacks a full exclusionary guideline but still provides strong usage signals.

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