codex_request_async

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the agent knows this can modify state. The description adds that the job is 'durable' and runs in the background, but does not elaborate on specific side effects, permissions, or rate limits beyond what annotations convey. It minimally extends the behavioral context.

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 extremely concise: two sentences that front-load the purpose and immediately guide the agent on next steps. Every word earns its place with no redundancy or fluff.

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 the high complexity (40 parameters, no output schema), the description is minimal and does not explain return values, error handling, or parameter interactions. It is adequate for the high-level goal but leaves gaps that the agent must infer from the schema or other tools.

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 the schema fully documents each parameter. The description adds no additional meaning for individual parameters; it only provides overall usage context. Baseline is 3 as per rubric.

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 the tool starts an OpenAI Codex CLI request as a durable background job, using a specific verb ('Start') and resource. It distinguishes itself from sibling tools like codex_request (synchronous) and other model-specific async tools by explicitly mentioning the async pattern and referencing llm_job_status and llm_job_result for polling and collection.

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 clear guidelines on how to use the tool: start the job, then poll with llm_job_status and collect with llm_job_result. This effectively tells the agent when to use this tool versus alternatives for asynchronous operations. It does not explicitly state when not to use it, but the context is sufficient.

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