guardvibe

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

With no annotations provided, the description carries the full burden. It explains output formats and gating but is ambiguous about whether it actually posts to GitHub APIs or merely formats output, and fails to clarify exit code behavior implied by 'block PRs' functionality.

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?

Three tightly constructed sentences (39 words) with zero waste: sentence 1 establishes purpose, sentence 2 covers scope and output targets, sentence 3 covers control mechanisms. Perfectly front-loaded and efficient.

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?

Adequate for input parameters given 100% schema coverage, but lacks necessary compensation for missing annotations and output schema—specifically omitting whether the tool returns formatted strings, posts side effects to GitHub, or sets exit codes for CI integration.

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?

Despite 100% schema coverage (baseline 3), the description adds semantic value by mapping parameters to functional roles: linking 'diff-only mode' to the diff_only parameter, 'severity gating' to fail_on, and output destinations to the format parameter.

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 opens with a specific verb+resource ('Review a pull request for security issues') and distinguishes from generic scanning siblings (like scan_file, scan_directory) by emphasizing PR-specific outputs (GitHub Check Runs, PR comments) and severity gating to block PRs.

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?

Implies clear context through mentions of 'GitHub Check Runs' and 'block PRs' suggesting CI/CD PR workflows, but lacks explicit when-not-to-use guidance versus similar siblings like scan_changed_files or scan_staged.

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