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

Annotations already declare read-only, idempotent, open-world behavior, so the description does not need to re-establish safety. It adds real context beyond that: the default window is 14 days reaching back 30, malicious-package reports are returned ahead of vulnerabilities, and KEV entries are folded in. Return fields (package, severity, fixed versions, CVEs, EPSS, advisory) are also disclosed, though pagination/truncation behavior is not.

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?

Two sentences, front-loaded with the core scope and ordering rule, with the long ecosystem list kept as a parenthetical clause. Dense but every clause carries scope information; it could tighten the model-name enumeration slightly.

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?

No output schema exists, so the description's enumeration of returned fields (package, severity, fixed versions, CVEs, EPSS, advisory) is necessary and present. Default window and KEV inclusion are covered; the main remaining gap is what limit does to results when the feed exceeds it, and no pointer to sibling advisory tools.

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 67%, so the schema carries most parameter meaning. The description adds taxonomy for the layer enum (agent frameworks, gateways, MCP, model serving, ML platforms, model libraries, AI apps, coding agents) and explains include_kev behavior implicitly ('CISA KEV entries in the same stack are included'). It adds nothing about limit, package, or since beyond what the schema already states.

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?

States a specific verb (list) and a precisely scoped resource: new advisories against AI/agent stack software, with the ecosystem enumerated (LangChain, LiteLLM, MCP, vLLM, MLflow, etc.). This makes it clearly distinct in substance from the generic list_cyber_advisories sibling, though the sibling is never named to make the boundary explicit.

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?

Usage is implied by 'new advisories' and the ordering rules (newest/most severe first, malicious-package reports first), which tells the agent what the feed emphasizes. However, there is no explicit when-to-use / when-not-to-use guidance and no pointer to list_cyber_advisories or get_cve for overlapping needs.

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