scan_dependencies

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

Without annotations, the description carries full burden. It discloses supported input formats, the max package limit (behavioral constraint), and that only vulnerable packages are returned. It does not explicitly state read-only behavior or auth needs, but the scanning action inherently implies safety, and the max limit adds transparency.

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 efficient: one sentence for purpose, a line for format support, and a brief args section. It is well front-loaded. Minor improvement could be separating the argument description more clearly, but it remains concise without wasted words.

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 an output schema (implied by context), missing return structure details are acceptable. The description covers input, supported formats, and key behavioral limits. It lacks explanation of error handling or malformed input, but overall provides sufficient context for typical use.

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?

The schema provides 0% parameter description coverage, so the description must compensate. It fully explains the dependency_list parameter: what formats it accepts (file contents or formatted lines) and the max 1000 packages. This adds significant meaning beyond the schema's bare type definition.

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 bulk scans dependencies for CVEs via OSV.dev, specifies supported formats (requirements.txt, package.json, pom.xml, or generic lines), and notes it returns only vulnerable packages. This is a specific verb-resource combination that distinguishes it from siblings like check_package_vulns.

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 use for bulk scanning with max 1000 packages, but does not explicitly state when to use this tool versus alternatives like check_package_vulns. It lacks directives on prerequisites or exclusions, leaving usage context implied rather than explicit.

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