guardvibe

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

No annotations are provided, so the description carries the full disclosure burden. It clarifies that the tool 'automatically reads staged files' without requiring input, but omits whether it performs mutations, what vulnerability classes it detects, or output behavior (exit codes, stdout vs stderr). 'Scan' implies read-only, but safety isn't explicitly confirmed.

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 sentences, zero waste. Purpose is front-loaded in sentence one, usage guidance in sentence two, and input requirements in sentence three. No redundant phrases or filler content.

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 low complexity (single optional parameter, no nested objects) and lack of output schema, the description adequately covers invocation context. However, it could improve by briefly characterizing the output (findings list vs. pass/fail) or behavior when no files are staged, since no output schema exists to document return values.

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%, establishing a baseline of 3. The description reinforces the optional nature of inputs ('No input needed'), which aligns with the schema showing zero required parameters, but adds no semantic detail about the format parameter's use cases beyond what the schema enum descriptions already provide.

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?

Description clearly states the specific action (scan), target resource (git-staged files), and purpose (security vulnerabilities). The phrase 'git-staged' effectively distinguishes this from siblings like scan_file, scan_directory, and scan_changed_files by specifying the exact git state being analyzed.

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?

Provides clear temporal guidance ('before every commit') and workflow context ('catch issues early'). However, it lacks explicit differentiation from scan_changed_files or scan_file for scenarios involving unstaged changes, and doesn't mention prerequisites like being in a git repository.

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