scan_file

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

With no annotations, the description carries the behavioral burden. It does disclose the key special case: audio/video files yield a notice that DEEP scan is needed. It does not disclose whether files are read-only/uploaded, return format, or any limits, which are material gaps for an unannotated tool.

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 compact sentences put the core purpose first and then the format/edge-case details. No filler or repetition of schema field names.

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 invoking with file_path and allow_deep, the description is close to sufficient, but the lack of an output schema and mention of return value shape means an agent cannot predict the scan result format beyond the DEEP-scan notice.

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%, so the baseline is met. The description adds useful context beyond the schema by explaining the DEEP-scan consequence for audio/video files and the OCR behavior for images.

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?

Names a specific action ('Scan a file') and target ('prompt injection and security threats'), and enumerates supported file types. The resource-level 'file' plus function name distinguishes it from siblings like scan_text, even though it doesn't name them.

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 gives clear context for when to invoke: given a text file, image, PDF, etc. It explicitly handles the audio/video exception, indicating a DEEP scan requirement. It does not name scan_text or scanner_info as alternatives or state when not to use it, so it stops short of a fully explicit routing.

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