rush_review

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

With no annotations provided, the description carries the full burden. It discloses the review criteria, the return shape, and the default heuristic behavior while flagging that use_llm=true invokes a configured model. This is solidly transparent, though it stops short of mentioning whether the operation is strictly read-only or what model/config is used.

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?

Every sentence earns its place: scope, review dimensions, return shape, and mode switching. The description is short, front-loaded with the essential purpose, and contains no filler.

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 tool with no annotations, four parameters, and many close sibling tools, the description is incomplete. The two undocumented parameters prevent fully correct invocation, and the absence of any sibling routing guidance further limits contextual completeness. The output schema mitigates return-value concerns, but it cannot fix the parameter and selection gaps.

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%, so the description must explain all parameters. It clarifies path and use_llm meaning, but use_graft and changed_files are completely unexplained. An agent cannot infer what use_graft does or how changed_files influences the review, which is a major 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?

The description clearly states a specific verb ('Review code at <path>') and enumerates concrete review dimensions: size, TODO density, missing docstrings, naming, complexity. This distinguishes it as an aggregate code-review tool rather than lint or typecheck. However, it does not explicitly name or contrast any sibling tool, so differentiation is implied rather than stated.

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 only guidance is about execution mode ('Default: heuristic' vs 'use_llm=true'), not about when to choose this tool over rush_lint, rush_complexity, or the many other siblings. There is no explicit use case, prerequisite, or exclusion stated, leaving the agent to infer when rush_review is the right choice.

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