Javaプロジェクトの脆弱性スキャン

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

With no annotations, the description carries the full burden and does well: it discloses the scan engine, the report shape (per-package vulnerability list with CVSS score, 5-level severity, fixed version, plus summary aggregates), and a critical non-obvious caveat that a transitivity warning invalidates a zero-finding result. It omits operational traits such as network dependency on the OSV API, credentials, or runtime expectations, which keeps it short of a 5.

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?

Four sentences, each load-bearing: purpose plus report format, report contents, supported build systems, and the safety caveat. The purpose is front-loaded and there is no filler or repetition.

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?

There is no output schema, so the description must describe returns and it does so concretely (severity-ordered JSON, CVSS, severity level, fixed versions, summary aggregation). Combined with the transitive-dependency caveat, an agent has enough to call and interpret the tool, though environment prerequisites (network access, scan duration) are not addressed.

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% and there is only one parameter (project_path), whose meaning is fully documented in the schema itself as a project directory or absolute path to pom.xml/gradle.lockfile. The description adds no syntax, path-form, or default detail beyond the schema, so the baseline of 3 is appropriate.

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 names a specific verb and resource (scanning a Java/Maven project with Google OSV-Scanner) and states exactly what is returned (known CVEs/GHSA in severity-ordered JSON). It narrows scope with supported build systems (pom.xml, gradle.lockfile), which implicitly separates it from scan_sbom and scan_java_artifact. However, it never names or contrasts a sibling explicitly, so an agent must infer the boundary against scan_project and scan_java_artifact.

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?

There is no explicit when-to-use/when-not-to-use statement or named alternative. Usage is only implied by the supported inputs (Maven pom.xml, Gradle gradle.lockfile), and the closing caveat tells the agent not to conclude safety when dependency_resolution.warning is present. That is useful operational guidance but not sibling routing.

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