codex_start_plan_workflow

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

The description mentions durability, long-running nature, and that it launches a new chat, but with no annotations, more behavioral context is expected (e.g., failure handling, cancellability, resource consumption). It does not contradict annotations as annotations are empty.

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 concise at two sentences, clearly front-loading purpose. However, it could include parameter guidance without losing conciseness.

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 15 parameters, many with complex enum options, and no annotations, the description is too minimal. It lacks information about required fields, default behaviors, and parameter interactions, leaving the agent underinformed for a tool of this complexity.

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?

Only 27% of parameters have schema descriptions; the tool description does not compensate by explaining key parameters like project_id, message, sandbox, or approval_policy. The description adds no parameter-level insight 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 clearly states the action: start a durable long-running orchestrator workflow via a new Codex chat in Plan Mode. It specifies return values (workflowId, threadId, planTurnId) and implies polling usage, differentiating it from sibling tools like codex_start_chat or codex_execute_plan.

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?

No explicit guidance on when to use this tool versus alternatives. The description hints at long-running orchestration and polling, but does not provide clear when-to-use or when-not-to-use context for the agent.

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