security_fetch_package_vulnerabilities

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. Description reinforces with 'Read-only. No side effects. Idempotent.' and adds an important behavioral detail: 1-hour cache. No contradictions.

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 moderately long but every sentence adds value. It is well-structured: starts with purpose, then details modes, then references, then source/cache, then feedback instruction. Could potentially be trimmed slightly, but it's efficient for the information density.

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?

For a tool with two modes, batch limits, and a multi-field output, the description covers everything: single/batch inputs, batch response structure, source verification (Google OSV.dev), caching behavior, and a fallback for inadequacy. Given the complexity (4 params, 0 required, but conditional logic), it is comprehensive.

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 coverage is 100% with descriptions, but the description adds significant context: explains the two parameter groups (single vs batch), how packages array overrides individual params, the batch response format (results, partial, failed_count), and details of each result. This goes well beyond the schema.

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 'Fetch all known CVEs for an open source package version or a batch of packages' and distinguishes single vs batch modes. It also references sibling tools for complementary tasks, so the purpose is specific and differentiated.

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 when-to-use instructions: single vs batch mode, max batch of 50, that batch overrides single params. Also advises using security_fetch_cve_detail for full CVE details and security_audit_sbom_vulnerabilities for SBOM files. Includes a fallback to report_feedback if the tool doesn't serve the need.

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