scan_file

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

No annotations are provided, so the description carries the full burden. It discloses the return format (line numbers, severity, CWE IDs, remediation) and auto-detection of language. However, it does not mention side effects (e.g., read-only nature), file size limits, supported file types, or whether network access is required. Adequate but not thorough.

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?

Two sentences with no wasted words. The purpose is front-loaded, and every sentence adds essential information. Excellent conciseness.

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?

For a simple tool with no output schema and few parameters, the description covers what the tool does, how it detects language, and what it returns. It is mostly complete, but could be improved by mentioning file size limits or supported file types to fully address the scanning context.

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?

Input schema covers both parameters with 100% description. The description adds value by explaining auto-detection of language from file extension and the optional nature of the language hint, which provides context beyond the schema's property descriptions.

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 clearly states the tool scans a single source file for vulnerabilities and secrets, with auto-detection of language. It specifies the return contents (line numbers, severity, CWE IDs, remediation). However, it does not explicitly differentiate from sibling tools like scan_input or scan_code, leaving some ambiguity.

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?

No explicit guidance on when to use this tool vs alternatives. The description only implies it is for single files, but does not mention when not to use it (e.g., for directories, use scan_directory) or provide any prerequisites.

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