Native Code Review

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds no behavioral context beyond what annotations provide; it does not explain what destructive actions might occur or what side effects the review has (e.g., modifying git state). It adequately describes the input scope but not the behavioral traits.

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: two paragraphs and a bullet list with no filler. It front-loads the core purpose and practical usage, making it easy for an AI agent to parse efficiently.

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?

While the description covers purpose and usage, it lacks information about the output format. Since there is no output schema, the description could explain the review return structure (e.g., JSON with issues, severity, line numbers). Additionally, it gives no details on limitations or error handling.

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 each parameter already has a clear description. The description adds general tips (e.g., 'Set workingDirectory to the target git repository') but does not provide additional semantic detail beyond what the schema offers.

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 runs 'Codex CLI's native diff-aware review' and specifies it is for reviewing uncommitted changes, base branch diffs, or a single commit. It distinguishes from sibling tools like 'codex' by targeting MCP clients that cannot run shell commands.

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 explicitly states when to use this tool ('for MCP clients that cannot run shell commands but need native Codex review') and provides alternatives: 'Use the codex tool with sandbox "read-only" for free-form review prompts.' It also gives tips on setting workingDirectory and choosing mode.

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