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

Beyond the readOnly and idempotent annotations, the description adds rich operational behavior: exactly one NVD call per invocation, per-source unavailability is noted, no matches yield a friendly 0-exposure result, and an overall exposure rollup with 'KEV present -> high' severity logic. These details give the agent accurate expectations about edge cases and data provenance. No contradiction with the annotations exists.

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?

Every sentence earns its place: purpose, data sources, output summary, edge cases, call-cost guarantee, and scope boundary. The description is dense but not padded, and the most important identifying information is front-loaded in the first sentence.

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 present, the description must explain return shape, and it does: total CVEs, CVSS severity band counts, KEV membership with actively-exploited CVEs, highest EPSS score, critical CVEs, top CWE types, overall rollup, and an evidence list. It also covers no-match and source-unavailability behavior, making the tool callable without missing expectations.

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?

The input schema has 100% description coverage for all four parameters, so the schema already carries the parameter semantics. The tool description adds only light value by explaining how vendor/product/keyword map to the NVD search behavior. This matches the baseline expected when schema coverage is complete.

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 opens with a specific verb and resource: 'One-call known-vulnerability exposure for a vendor/product/package.' It clearly distinguishes this tool from individual lookups by presenting it as an aggregate that fans out to NVD, KEV, EPSS, and CWE sources. The explicit out-of-scope note about package-registry maintenance also prevents confusion with package-focused siblings.

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 'one-call' framing and the detailed summary of fused outputs make it clear when to choose this tool over raw CVE or EPSS lookups. The explicit 'Package-registry maintenance/staleness signals are out of scope' provides a concrete when-not boundary. However, it does not name sibling tools directly as alternatives, such as cve_search_by_vendor or kev_status_check, so the guidance is strong but not fully explicit.

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