claude_review_followup

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

No annotations, so the description carries the full burden. It does disclose a real behavioral trait — the follow-up reuses the original reviewer context via session_id — but says nothing about what happens with an invalid/expired session, cost implications of maxBudgetUsd, or how timeoutMinutes affects a long re-check. Useful but incomplete for an annotation-free, stateful tool.

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?

Two tight sentences, front-loaded with the core action and followed by the required input. The parenthetical examples add concrete value rather than filler, though the sentence is slightly dense.

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?

For a 7-parameter tool with no output schema and no annotations, the description covers the essential workflow (which session to pass) but leaves four parameters and the return behavior unexplained. It is adequate to invoke correctly in the happy path but not to handle edge cases.

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 43%: sessionId, message and repoPath are documented in the schema, while model, maxBudgetUsd, outputLanguage and timeoutMinutes are entirely undocumented in both schema and description. The description only echoes sessionId and adds nothing about the four silent parameters, so it fails to compensate for the coverage 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+resource — 'Continue the conversation of a previous claude_code_review run' — and immediately distinguishes it from the sibling that starts a fresh review. The parenthetical examples ('为什么第 2 条是问题？', 're-check after my fix') make the intended scope unambiguous.

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?

Clear usage context: this is for follow-ups to an existing review and requires the session_id returned by claude_code_review. It does not explicitly name the alternative ('start a new review with claude_code_review'), but the session-continuation framing makes the routing condition clear.

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