codex_review

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces that with 固定只读 and adds value beyond them: defect-focused output, severity-sorted results with file:line, async/wait semantics identical to codex_spawn, and a task id return. Timing context (审查通常 1~3 分钟) is also supplied.

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?

Front-loads the core purpose and return shape, then enumerates scopes, then the sibling routing. Dense but every clause carries information; only the repeated scope enumeration overlaps slightly with the enum in the schema.

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?

With no output schema, the description correctly compensates by describing the return (severity-sorted, file:line issue list) and the async task-id behavior. It is complete enough for an agent to call it correctly without opening the schema.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: the scope→value mapping (分支名 / sha / 自定义说明) and the note that uncommitted needs no value. It does not explain detach's relationship to the async task id, leaving one minor gap.

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?

States a specific verb and resource (审查改动 via Codex 内置审查模式), the mode's character (固定只读、以找缺陷为主), and the return shape (按严重度排序、带文件行号的问题列表). It explicitly distinguishes itself from the sibling codex_spawn by intent (改代码 vs 挑毛病).

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?

Gives explicit routing: use codex_spawn to change code, use this only to find faults. It also breaks down when to pick each scope value (uncommitted/base_branch/commit/custom) with the value semantics for each, so the agent can select without inference.

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