Look up a CVE by ID and get a compact summary: description, CVSS score & severity, vector, CWE weakness, publish date, and references. Source: NVD (NIST).
| Name | Required | Description | Default |
|---|---|---|---|
| cve_id | Yes | e.g. CVE-2021-44228 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey safety and behavior. It states the output fields and source but does not mention error handling (e.g., invalid or missing CVE), rate limits, or authentication requirements. The simple lookup nature is mostly transparent.
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 two sentences long: the first clearly states the purpose and output, and the second credits the source. Every word is necessary and there is no fluff.
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 tool is simple with one parameter and no output schema. The description fully covers what the tool returns and its source. It could mention potential error cases or the expected input format more formally, but the schema already provides an example.
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 the sole parameter 'cve_id' having an example in its description. The tool's description reinforces that the parameter is a CVE ID but adds no new detail 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 the action ('Look up a CVE by ID') and provides a specific list of returned fields (description, CVSS score, severity, etc.). It also mentions the data source (NVD NIST), which distinguishes it from sibling tools like audit_dependencies and package_vulnerabilities.
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 implies when to use (to get a summary of a specific CVE) but does not provide explicit guidance on when not to use it or suggest alternatives like package_vulnerabilities for broader vulnerability scanning.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct security vulnerability task: scanning a manifest, looking up a specific CVE, or listing package vulnerabilities. No overlap in purpose.
All use snake_case but pattern varies: 'audit_dependencies' is verb_noun, 'cve_lookup' is noun_verb, 'package_vulnerabilities' is noun_noun. Descriptive but inconsistent.
Three tools cover the core vulnerability intelligence needs without excess. Well-scoped for the server's purpose.
Covers manifest scanning, CVE lookup, and package vulnerabilities. Minor gaps like batch operations or version range checks, but sufficient for typical use.