codex_start_plan_workflow

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

No annotations exist, so description bears full responsibility. It states the workflow is durable and returns immediately, but fails to disclose side effects, error handling, rate limits, or any behavioral traits beyond the high-level flow. Insufficient for a complex tool with 15 parameters.

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 with no fluff. It front-loads the core action. Could be slightly more informative without losing efficiency, but remains effective.

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 tool's complexity (15 parameters, many with enums, no annotations, low schema coverage), the description is incomplete. It omits explanation of output schema, parameter usage, and full lifecycle details beyond the one-liner.

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 27%, requiring the description to compensate. However, the description adds no parameter-level information beyond implying project_id and message. Most parameters (e.g., model, sandbox, approval_policy) remain unexplained.

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 uses specific verb 'start' and resource 'durable Plan Mode workflow', clearly distinguishes from sibling tools by outlining the workflow lifecycle (start, poll, approve), and states when to use: 'when a plan must be prepared before implementation'.

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?

Provides explicit next steps: poll codex_get_workflow_status, then call codex_approve_plan. Clearly implies usage context (plan preparation before implementation), but does not explicitly list when not to use or mention alternative tools.

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