cybersecurity-vuln-mcp

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

Without annotations, the description carries the full behavioral disclosure burden. It identifies the data source (NIST NVD) and search capabilities but omits critical behavioral details: return format (since no output schema exists), pagination/limit behavior, whether the search performs partial matching on keywords, and rate limit considerations.

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 single sentence is front-loaded with the core action and resource, contains no filler words, and efficiently summarizes the search capabilities. However, given the tool's complexity (6 parameters, no output schema, many siblings), 'appropriately sized' might warrant additional sentences for behavioral context.

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?

The description acknowledges the three primary filters but notably omits the `hasKev` parameter (actively exploited filter) despite this being a significant differentiator from other vulnerability tools. Given the lack of output schema and annotations, the description should explain return values or result structure, which it fails to do.

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?

With 83% schema description coverage (5 of 6 parameters documented), the baseline is appropriately 3. The description maps to the keyword, severity, and date parameters but adds no additional semantic context—such as syntax examples for date formats or clarification that keyword searches perform substring matching—that would compensate for the undocumented `limit` parameter.

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 the verb (Search), resource (NIST NVD CVEs), and primary filtering dimensions (keyword, severity, date range). However, it does not explicitly differentiate from siblings like `vuln_lookup_cve` (likely for specific CVE IDs) or `vuln_by_vendor`, leaving some ambiguity on when to select this tool versus alternatives.

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 description provides no guidance on when to use this tool versus the six sibling vulnerability tools. It does not mention that this is appropriate for broad discovery versus specific CVE lookups, nor does it reference the `hasKev` parameter's utility for finding actively exploited vulnerabilities compared to the dedicated KEV sibling tools.

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