Apex Code Review

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

Annotations indicate readOnlyHint=false, destructiveHint=false, openWorldHint=true. The description adds behavioral details: runs in sandbox, async for large repos, limited to 3 submissions per day, and returns audit_id. No contradictions with annotations.

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 yet comprehensive, front-loading the main purpose and then detailing behavior, usage, and limitations. Every sentence adds necessary information.

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 (multiple input modes, async behavior, output with score and findings), the description covers all key aspects: input types, processing steps, output format, async behavior, and daily limit. Output schema exists, but description explains return values sufficiently.

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% with descriptions for all three parameters. The description adds context: mutually exclusive parameters, usage scenarios (repo vs source vs audit_id), and clarifies that github_url clones repo and analyses Solidity/Rust. This adds semantic value beyond the schema.

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 a preliminary security audit on smart contracts, accepts GitHub URL or pasted Solidity source, runs static analysers and AI review, and returns a score and findings. It is specific and distinguishes from sibling tool names.

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 says 'use this when asked to audit, review, or assess the security of a project's contracts or on-chain code.' It also provides context on when not to use (not a substitute for professional audit) and notes async behavior for large repos.

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