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

Adds substantial behavior beyond the readOnly/openWorld/idempotent annotations: confirmed vs reported tiers, ordering rules, result fields, indicator-count semantics ('absent when unknown, never 0'), quota cost with a key, and IP rate limiting without one.

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 core definition is front-loaded in the first clause, and the following material on tiers, ordering, fields, and quota is relevant. It is dense and reads as one long block, which costs some structure but not enough to call it wasteful.

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?

There is no output schema, so the description carries the return-value burden and does so thoroughly: severity, CVSS, EPSS, first/last evidence, KEV date, patch status, sources, and indicator counts. Ordering, caveats, and access cost are also covered.

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%, so the schema already documents both days and limit including defaults and bounds. The description repeats the default-7 window but adds no syntax or usage nuance beyond the schema, making 3 the appropriate baseline.

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 resource and qualifier: CVEs with attested exploitation in a time window, with confirmation tiers. This clearly distinguishes it from a general recent-CVE list or per-CVE lookup such as get_cve or recent_cves.

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?

Sets clear context for use: exploitation-attested CVEs over a window, with the caveat that absence does not mean not exploited, and points to get_cve for single-CVE follow-up. It does not explicitly contrast with recent_cves, so the when-not-to-use routing is not fully closed.

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