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 effectively discloses the return structure (before/after code, severity, line numbers) and crucially clarifies that the AI (not the tool itself) applies the patches, implying non-destructive read-only behavior. However, it omits auth requirements, rate limits, or explicit confirmation that source files are not modified.

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 that are all front-loaded and high-value. The first states the core operation, the second clarifies the agent's role in applying fixes, and the third details the return structure. No redundant words or repetition of schema details.

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 lack of output schema, the description adequately compensates by detailing the return structure (severity, line numbers, before/after code). It addresses the tool's place in the workflow (generating patches for AI application). Minor gap: does not explicitly mention that only 'code' and 'language' are required inputs, though this is clear from the 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?

Schema description coverage is 100%, establishing a baseline of 3. The description mentions 'structured fix data' which loosely aligns with the 'format' parameter options, but does not add semantic meaning beyond the schema for parameters like 'framework' (e.g., explaining that it tailors security rules to specific frameworks) or elaborating on the 'code' input requirements.

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 specific verbs ('analyze', 'return fix suggestions') and clearly distinguishes from siblings like check_code or analyze_dataflow by emphasizing 'concrete patches' and automatic fix capabilities. It specifies the resource (code) and the unique value proposition (patches for AI application).

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 implies when to use the tool (when you want 'fix suggestions' and 'concrete patches' that the AI can apply automatically), but lacks explicit guidance on when to choose this over similar siblings like check_code or analyze_dataflow. No 'when-not-to-use' guidance is provided.

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