guardvibe

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

With no annotations provided, the description carries full disclosure burden. It successfully notes filesystem I/O behavior and return structure (security score A-F, metadata). However, it omits critical safety information (read-only vs destructive), permission requirements, or performance characteristics for large directories, leaving gaps in behavioral disclosure.

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?

Five sentences, zero waste. Front-loaded with core purpose, followed by I/O behavior, return values, metadata details, and parameter-specific guidance. Every sentence earns its place with high information density and no redundancy.

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?

Compensates for missing output schema by describing return values (score, findings, metadata). However, given the tool's filesystem access and security context, the lack of safety/permission disclosure (coupled with no annotations) leaves the description incomplete for safe agent operation.

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 100%, with all five parameters (path, recursive, exclude, format, baseline) well-documented in the schema itself. The description adds minimal semantic value beyond the schema—merely restating the baseline comparison functionality already described in the parameter definition. Baseline score appropriate for 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 opens with a specific verb ('Scan') and clear resource ('entire project directory'), explicitly targeting 'security vulnerabilities.' It effectively distinguishes from siblings like scan_file (single file), scan_dependencies (dependencies), or scan_changed_files (diff-only) by emphasizing 'entire project 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 implicit guidance via 'Reads files directly from the filesystem — no need to pass file contents,' indicating when to use this over content-passing tools. It also notes baseline usage for comparisons. However, it lacks explicit 'when to use vs alternatives' guidance regarding sibling tools like check_project or repo_security_posture.

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