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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: it discloses how the ranking is computed (exploitation, EPSS, CVSS, automatability) and that results are scoped to vulnerabilities with activity in a time window, which explains why two seemingly similar queries can return different sets. It omits the default result size and tie-breaking behavior, which is why this is not a 5.

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?

One sentence, front-loaded with the actionable framing "What to patch first" before the technical qualifiers. The parenthetical list of scoring inputs is an efficient way to convey the ranking model without extra sentences. It is dense, borderline packed, which keeps it from a 5.

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?

With six optional parameters, a rich annotation set and an output schema that carries return values, the description covers the essential unknowns: what makes an item 'top priority' and what the filters do to that set. The remaining gaps, default limit of 15, the 50 cap and whether filtering happens before or after ranking, are minor and partly recoverable from 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 67%, so the schema already documents most parameters, including the enum for window and the exact-name conventions for vendor and product. The description adds the useful semantic point that ecosystem, vendor and product act as narrowing filters on the ranked set, which is more than the schema states on its own. It says nothing about kev or limit, leaving those to 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 names the resource (vulnerabilities) and the specific selection logic: ranked by priority score composed of exploitation, EPSS, CVSS and automatability, restricted to items with recent activity. That is far more precise than a bare name restatement. It stops short of naming a contrasting sibling such as list_feed or search, so an agent must infer that this is the ranked/prioritized view rather than a general listing.

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 framing "what to patch first" clearly implies the use case: prioritization and patch triage rather than lookup or browsing. However, there is no explicit when-not guidance and no pointer to an alternative when an agent wants a single CVE's details (get_vulnerability) or a broader listing (list_feed). Usage is implied rather than stated.

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