codex_start_review_workflow

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

Annotations are empty, so the description carries full responsibility. Although it mentions 'durable' and 'fast workflow ack', it does not disclose whether the tool is read-only or destructive, what side effects occur (e.g., starting a background process), authentication requirements, rate limits, or if changes are reversible. For a tool that presumably mutates state, this is insufficient transparency.

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 two sentences with no fluff, front-loaded with the core purpose. It could be slightly longer to cover essential parameter hints without becoming verbose, but it is efficient for its intent.

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, 4 enums, required output schema), the description is severely lacking. It omits any guidance on parameter interdependencies, workflow lifecycle, error conditions, or how to interpret the ack. The output schema is present but not referenced. The description alone is insufficient for an agent to correctly invoke the tool.

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 0% (no parameter descriptions in schema). The text description does not explain any of the 15 parameters, their defaults, or which combinations are required (only target_type is required). It adds no meaning beyond the raw schema, leaving the agent to guess semantics like how target_type relates to base_branch or commit_sha.

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 verb 'Start', the resource 'durable Codex code review workflow', and the mechanism 'through app-server review/start'. It distinguishes this tool from siblings like codex_start_chat and codex_start_plan_workflow by specifying the workflow type, and it mentions the asynchronous nature (fast ack, poll for status).

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 explains the immediate return (fast ack) and directs the agent to poll codex_get_workflow_status for progress and final report. It implicitly positions this tool for starting a code review workflow, and while it doesn't explicitly state when not to use it or name alternatives, the sibling tools provide context, and the instruction to poll is clear. Could be improved by explicitly saying 'Use this for code review workflows; for chat workflows use codex_start_chat'.

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