Look up recent CVEs from the NIST NVD feed, optionally filtered by keyword. Returns id, severity, score and summary.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (1-25). Defaults to 10. | |
| keyword | No | Optional keyword, e.g. "wordpress" or "openssl". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses return fields (id, severity, score, summary) and the 'recent' scope, but does not address potential side effects (e.g., network calls, rate limits, data freshness) or explicitly state that it is read-only. However, the behavior is inherently non-mutating and simple enough for a baseline score.
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 a single, well-structured sentence that immediately states the action, resource, and expected output. No extraneous words or repetition—every word adds value.
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 simple read-only lookup with two optional parameters and no output schema, the description adequately covers purpose, optional filtering, and return fields. It does not over-explain, leaving trivial details to the schema. Minor omission: no mention of default limit or pagination behavior, but these are present in the schema.
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 description coverage is 100% for both parameters (limit and keyword), so the description adds little beyond restating the keyword filter. It does imply 'recent' relates to the data source but not parameter details. Baseline 3 is appropriate given the schema already fully documents them.
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 uses a specific verb 'Look up' and clearly identifies the resource ('recent CVEs from the NIST NVD feed') with an optional filter. It distinguishes itself from sibling tools like scan_website or get_fix_guidance by focusing solely on CVE lookup.
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 clearly conveys the tool's purpose and context: fetch recent CVEs with optional keyword filtering. Sibling tools are unrelated, so no explicit exclusion is necessary; the usage context is obvious and unambiguous.
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.
Tools are mostly distinct: billing, scanning websites, scanning AI agents, CVE lookup, and remediation guidance all serve clear separate purposes. The main overlap is between compliance_report and scan_website, both assessing sites but from different angles; however descriptions clarify the distinction.
Most tools follow verb_noun pattern (buy_credits, check_credits, get_fix_guidance, get_pricing, lookup_cves, scan_agent, scan_website). 'compliance_report' is a noun phrase rather than a verb action, slight deviation but not confusing.
8 tools is well-scoped for a security scanning service. Each tool covers a necessary function: billing, pricing, scanning, compliance, CVE lookup, and remediation guidance, without unnecessary bloat.
The surface provides core lifecycle coverage for the domain: scanning (web and AI agent), compliance assessment, vulnerability intelligence, fix guidance, and credit management. Minor gaps exist like scan history or saved reports, but the tools handle real-time needs without dead ends.