scan_packages

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 only states the basic action (scan and check) without disclosing side effects, safety implications, or whether it is read-only. Significant gaps remain for a tool with no annotations.

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?

The description is two sentences: the first states the purpose, the second provides essential verbosity guidance. There is no fluff, and key information is front-loaded. Every sentence earns its place.

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 tool has 3 parameters, no output schema, and no annotations, the description adequately covers purpose and verbosity but misses context such as what 'hallucinated' means in output, expected return format, or any preconditions. It is minimally viable but not rich.

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 coverage is 100%, so the base is 3. The description adds value by explaining verbosity levels beyond the schema's enum descriptions (e.g., 'minimal for counts', 'compact for flagged packages'). This helps an agent choose the right verbosity for the task.

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's purpose: scanning code for package imports and checking for hallucinated (AI-invented) packages. The verb 'scan' and resource 'package imports' are specific, distinguishing it from sibling tools like check_package or sbom_check_hallucinations.

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 provides guidance on verbosity levels (minimal, compact, full) for using the tool, but does not explicitly state when to use this tool over alternatives or any exclusions. Usage context is implied but not directly addressed.

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