scan_lockfile

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

With no annotations, the description bears full burden. It discloses the tool reads a lockfile, queries multiple sources, enriches with EPSS, and returns a prioritized report with fix recommendations. It notes default filtering (suppresses low-priority CVEs) and the effect of show_all=True. However, it omits potential issues like file not found, unsupported format, or long execution time, which would enhance 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 concise (7 sentences) and well-structured: a short summary, a bullet list of supported formats, default behavior note, and explicitly labeled 'Args' section. Every sentence adds value with no redundancy.

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 low parameter count and presence of an output schema, the description adequately summarizes the tool's function and parameters. It includes default filtering behavior and the effect of show_all. Minor gaps include not addressing file accessibility, format validation, or expected response time, but overall complete for this complexity level.

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 description fully documents both parameters, adding meaning beyond the schema titles: lockfile_path requires 'Absolute path', show_all shows 'all vulnerabilities including low-priority ones'. This covers all parameters with clear, actionable guidance, despite the schema having 0% description coverage.

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 lockfile for vulnerabilities, enumerates supported formats (package-lock.json, requirements.txt, go.sum), and specifies data sources (NVD + GitHub Advisories, EPSS). It differentiates from siblings like scan_project (broader scope) and check_package (single package), making the specific function immediately clear.

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 explains when to use the show_all parameter, but does not provide explicit guidance on when to choose this tool over siblings (e.g., scan_project for a full project scan, lookup_cve for a specific CVE). No 'when not to use' or alternative recommendations are given, leaving the agent to infer appropriate contexts.

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