check_vulnerabilities

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

The annotations already cover read-only, open-world, idempotent, and non-destructive behavior. The description adds useful context that partial source failures are reported per source, which is meaningful behavior beyond the annotations, though it does not mention rate limits or output structure.

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?

Two short sentences with no wasted wording, and the primary usage mode is front-loaded before the partial-failure note.

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?

With no output schema, the description should explain what a vulnerability query returns, but it only mentions per-source partial failures. It also omits details about the ecosystem parameter and batch constraints, leaving significant gaps for an open-world query tool.

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 0%, so the description must carry parameter semantics. It distinguishes the name/version path from the packages batch path but says nothing about the ecosystem parameter, enum values, batch limits, or the fact that top-level parameters are technically not required.

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 states a specific verb and resource: query OSV.dev for a single package@version or a batch. It clearly distinguishes the single-package and batch modes, though it does not explicitly differentiate itself from siblings like audit_lockfile or get_package.

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?

It implies when to use the tool by naming OSV.dev and the two supported input modes, but it gives no explicit guidance about when to choose this over audit_lockfile, license_check, or get_package.

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