Search CVEs

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

Annotations already declare read-only, idempotent, open-world behavior, so the description need not restate safety. It adds genuinely non-obvious traits: results are cached for 15 minutes, and NVD evaluates every filter so totalResults is the exact upstream total, plus how to paginate via nextCursor. Missing details like rate limits or cache-staleness implications keep it below 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?

Three sentences, front-loaded with purpose then rules then caching/pagination, with no filler. The opening filter enumeration slightly overlaps with what the schema already lists, so it is not maximally economical, but every clause carries usable information.

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 19-parameter, nested-object tool with an output schema present, the description covers the essential non-schema gaps: constraint interactions, window caps, caching, exactness of totals, and pagination mechanics. An agent can call it correctly without opening the schema, though sibling routing is the one untouched area.

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 95%, so the baseline is 3, but the description adds cross-parameter semantics the schema only partially encodes: the keyword/keywordExactMatch and cpeName/isVulnerable dependencies, the exclusivity pair, and the shared 120-day window limit. It also clarifies that statuses and filters are applied upstream by NVD, which is meaning beyond the field-level text.

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?

States a specific verb+resource ('Search CVE records') and enumerates the exact NVD 2.0 filter dimensions the tool accepts, so the agent knows precisely what surface it covers. It is clearly distinct from get-style siblings in name and behavior, but never explicitly names those siblings or contrasts itself with them, keeping it short of a 5.

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 'Rules' sentence gives real operational constraints (keywordExactMatch requires keyword; isVulnerable requires cpeName; cpeName/virtualMatchString mutually exclusive; 120-day windows) and explains pagination. However, there is no guidance on when to choose this over sibling tools like nvd_get_cves or nvd_get_recent_cves, which is the main 'when-to-use' question for a search tool.

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