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

Annotations already cover read-only, idempotent, and non-destructive. The description adds valuable context: data is LIVE, ranking is deterministic (no model in the loop), and it explains the ranking factors (CISA KEV, CVSS, EPSS, ransomware). This goes beyond the annotations.

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?

Three tight sentences: what it does, when to use it, and a key behavioral note. Each sentence earns its place, and the main purpose is front-loaded with 'LIVE: CVEs being exploited...'.

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?

The description names the output fields (CISA due date, patch availability, ranking factors) and covers use cases. With no output schema, this gives enough context for an agent to understand the return shape, though it doesn't detail exact format or pagination behavior.

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 only parameter 'limit' is fully described in the input schema (coverage 100%), including default and range. The description does not add parameter details, but the schema is sufficient, so the baseline score of 3 applies.

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 explicitly states the tool lists actively exploited CVEs (CISA KEV) ranked by a specific formula (CVSS × EPSS × ransomware use), which is a distinct resource and purpose compared to siblings like list_active_incidents or provider_reliability.

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?

It lists three concrete use cases: 'what should we patch first', 'is CVE-X exploited', and recent vulnerabilities beyond training data. It does not explicitly name alternatives or exclusions, but the use cases are clear and sufficient for an agent to know when to invoke it.

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