get_vulnerabilities

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

Annotations already declare readOnly, idempotent, non-destructive, and openWorld. The description adds the return structure ({vulnerability_count, vulnerabilities[] with id, severity, cvss, fixed_in}) and clarifies version scoping. This provides useful context beyond annotations, though the 'specified version' mechanism is ambiguous.

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 compact and well-structured, with a leading purpose clause followed by clear USE WHEN and RETURNS sections. Every sentence adds value, and the formatting aids quick parsing by an agent.

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 provides a return format, which is good. However, the ambiguity around specifying a version (since no version parameter exists in the schema) is a notable gap. For a simple two-parameter tool, the description is mostly complete but falls short on this critical detail.

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 explain parameter semantics, but it only implicitly references the version via 'or specified' without detailing how to specify it (e.g., package@version). It does not clarify the package string format or the ecosystem enum values beyond what the schema already provides, leaving significant ambiguity.

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 that the tool returns CVE/OSV advisories for a package, either for the latest or a specified version. This specific verb+resource+scope distinguishes it from sibling tools like get_known_bugs or check_malicious, which address different concerns.

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?

Provides explicit 'USE WHEN' conditions, including security-sensitive projects and user queries about CVEs, plus a prerequisite ('you already know the pkg exists'). However, it does not explicitly mention when not to use it or name alternative tools for other scenarios, so it lacks full exclusions.

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