Get the CISA Known Exploited Vulnerabilities (KEV) catalog. Returns the most recent N entries plus catalog metadata. Refreshed daily at 06:30 UTC. License: US Government public domain. ~1500 actively-exploited CVEs.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Top-N most-recent entries (1-50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully carries the burden. It discloses that the tool is read-only (getting catalog), non-destructive, publicly available, and has a defined update frequency. Mentions approximate catalog size ('~1500 actively-exploited CVEs') and license, giving the agent a clear understanding of behavioral traits.
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 extremely concise, with three sentences that are front-loaded with the main purpose. Each sentence provides unique value: purpose, behavior (returns N entries + metadata), schedule, license, and scope. No wasted words.
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?
Given the tool's low complexity (one parameter, no output schema), the description is complete. It covers what the tool does, what it returns, when it is updated, and the data's public domain nature. The agent has enough information to use the tool 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?
The input schema has 100% coverage for the only parameter (limit) with a clear description ('Top-N most-recent entries (1-50)'). The tool description does not add any additional meaning beyond what the schema provides, so the baseline score of 3 is appropriate.
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?
Clearly states 'Get the CISA Known Exploited Vulnerabilities (KEV) catalog' with a specific verb and resource. The description distinguishes it from sibling tools like get_cve_record and get_epss_score by focusing on the KEV catalog. It also specifies what is returned (most recent N entries and catalog metadata).
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?
Provides clear context on when to use (to get recent entries) and includes refresh schedule ('Refreshed daily at 06:30 UTC') and license ('US Government public domain'). It implicitly differentiates from siblings by focusing on actively exploited CVEs, but does not explicitly state when not to use or suggest alternatives.
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.
Several security/vulnerability tools (check_ai_supply_chain_risk, get_cve_record, get_osv_advisory_by_id, get_osv_advisory_for_package) have overlapping purposes, making it potentially confusing to choose the right one. Other tools are more distinct, but the ambiguity in this cluster lowers the score.
All names are snake_case and mostly follow a verb_noun pattern, but the verbs are inconsistent (check, get, list, lookup, query, register, route, search, submit, whats_new). Some tools use 'get' while others use 'check' for similar retrieval actions, and 'whats_new' does not fit the verb_noun pattern.
With 27 tools, the count exceeds the 25 threshold for 'too many', even though the broad scope spans many domains. The sheer number makes the server feel heavy and harder to navigate.
The server covers a wide range of data domains, but notable gaps exist: no management of watch subscriptions (only register), no CVE search, and no model search. Write operations are minimal, leaving some workflows incomplete.
