cve_lookup

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

With no annotations, the description carries full behavioral burden and does well: it discloses data sources (NVD, OSV), the shape of returned fields (description, CVSS score/vector, CWE, CISA known-exploited flag; affected packages, fixed versions), plus cost ($0.009 USDC/call) and p99 latency (4000ms). It omits auth requirements and error/failure behavior, which for a paid external-API tool would be valuable.

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?

Single dense paragraph that is front-loaded with the purpose and mode split, then parameters, then cost/latency. Nearly every clause earns its place; the parenthetical data-source inventory and ecosystem list are dense but informative rather than wasteful.

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?

No output schema exists, so the description appropriately explains returned data for both modes, and it covers the two most commonly missing metadata classes (cost and latency). Gaps remain around auth/quota requirements and exact error semantics for a paid third-party-backed call, but an agent has enough to invoke it correctly.

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 only 40% (package and version are undocumented in the schema), so the description must compensate and largely does: it names all five parameters, defines the two usage modes, and adds the meaningful hint that version is 'recommended'. It does not clarify flag precedence or that limit applies only to the package-check mode, but it adds real value over 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?

States a specific verb and resource and clearly enumerates two distinct modes: lookup by CVE/GHSA id and package-version vulnerability check, naming data sources (NVD, OSV). However, it does nothing to differentiate from the sibling 'package_check', which appears to overlap with the package-vulnerability mode, leaving an agent to infer the boundary.

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 'cve_id, or package + ecosystem (+ version, recommended)' phrasing implies which parameter combination to use for each mode, which is useful. But it offers no explicit when-to-use vs when-not, no prerequisites, and no routing against the overlapping 'package_check' sibling.

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