model_scanner__scan_file

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

With no annotations, the description carries the full burden and does substantial work: it discloses the concrete detection logic (pickle globals inside PyTorch zip containers, malformed safetensors headers, Keras Lambda RCE, ONNX path traversal). It does not state whether the operation is read-only, is side-effect free, or whether findings carry severity, but the detection behavior is unusually well disclosed.

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?

A single front-loaded sentence that puts the verb and scope first, then the risk catalogue. The risk list is dense but each item earns its place by naming a concrete format-specific attack, though the sentence is long enough to strain readability.

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 scanner with no output schema, the description should hint at what a finding looks like (categories, severity, counts), and it does not. It covers what is checked but leaves the result shape entirely unspecified.

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?

There is only one parameter and the schema already documents it at 100% coverage, including the accepted file extensions. The description adds no syntax, path-resolution, or format guidance beyond the schema, so the baseline 3 applies.

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?

States a specific verb (Scan) and resource (a single ML model file) and enumerates the exact risk classes it detects. It is clearly distinguishable from siblings like model_scanner__scan_directory and model_scanner__list_patterns because it scopes itself to one file.

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 phrase 'a single ML model file' implies when to use it, and the enumerated checks imply the target artifacts. However, it never explicitly says to use this instead of scan_directory when you have one file, nor does it name alternatives or state prerequisites.

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