guardvibe

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It successfully explains the unique cross-file analysis behavior (detecting mismatches between middleware and routes), but fails to disclose safety characteristics (read-only vs destructive), permission requirements, or whether the tool writes results to disk versus returning them. The term 'Audit' implies read-only access but this is not explicit.

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 consists of exactly two high-density sentences. The first establishes the core function and scope, while the second delivers the unique value proposition with concrete examples. There is no redundant text or filler; every word contributes to clarifying the tool's specific niche in cross-file configuration analysis.

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 complexity of analyzing multiple configuration files for security interactions, the description adequately covers the tool's purpose and detection capabilities. However, without an output schema, it could benefit from a brief indication of what the audit returns (e.g., 'returns a security report'). The listing of specific vulnerability types (headers, routes, secrets) partially compensates for the missing output schema.

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?

The input schema has 100% description coverage, with 'path' documented as 'Project root directory to audit' and 'format' as 'Output format.' The description does not add semantic meaning beyond what the schema already provides (e.g., no guidance on path format, relative vs absolute, or when to choose markdown vs json). Baseline score of 3 is appropriate given high schema coverage.

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 uses a specific verb ('Audit') with clear resource scope ('project configuration files') and lists exact file types (next.config, middleware/proxy, .env, vercel.json). It explicitly distinguishes from siblings by emphasizing 'cross-file security issues' and 'gaps that single-file scanning misses,' clearly differentiating from scan_file/scan_directory.

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 provides clear context for when to use this tool by contrasting it with single-file scanning approaches. It lists specific detection scenarios (missing security headers, unprotected routes, exposed secrets, middleware/route mismatches) that indicate appropriate use cases. However, it does not explicitly name sibling alternatives like scan_file or audit_mcp_config that should be used instead for single-file analysis.

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