Kevscope CVE Check

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

Annotations already declare this a safe, idempotent, read-only lookup, so the safety profile is covered. The description adds useful behavior beyond them: it names the returned data sets (KEV, EPSS, CVSS, SSVC, sorted verdict with reasons) and the 20-item batch ceiling, telling the agent this is a batched multi-source lookup rather than a single-record fetch.

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 ordered as trigger, input contract, then output, with zero filler. The most decision-relevant clause ('Use this when…') is front-loaded and the example phrasings are compact.

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 no output schema, the description does the work of summarizing the return payload (KEV status, EPSS, CVSS, SSVC, sorted verdict with reasons), and it covers input form and batch limit. The one meaningful gap is the absence of any comparison to the sibling 'recent_kev', which an agent choosing between two KEV-aware tools would benefit from.

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 0%, so the description carries the burden, and it delivers something the schema cannot express: the argument accepts raw text containing CVE IDs, not just a clean array of IDs. It also restates the 20-item cap, which is already in the schema. The dual-mode input semantic is the genuinely additive part.

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 states a specific verb and resource ('Check and prioritise CVEs') and enumerates the exact signals it evaluates (CISA KEV, EPSS, CVSS, SSVC) plus a sorted verdict. That is far more than a restatement of the name, but it never distinguishes itself from the sibling 'recent_kev', which also surfaces KEV data, so an agent cannot fully separate the two from text alone.

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 gives explicit trigger conditions with quotes ('is CVE-… exploited', 'prioritise these CVEs', 'KEV status', 'EPSS score'), which is clear when-to-use guidance. It stops short of stating when NOT to use it or pointing to 'recent_kev' as the alternative for a KEV-feed-style query, so the routing burden remains partly on the agent.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered without the description. The description adds no behavioral context such as the default 30-day window, the 100-result cap, freshness/lag of the CISA feed, or pagination behavior, so it earns only the baseline-plus credit.

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?

A single sentence, front-loaded with the trigger condition followed by illustrative examples — nothing wasted. It loses a point only because the parenthetical is dense and the 'product' reference does not correspond to any schema field.

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?

For a read-only, zero-required-parameter lookup with sensible defaults and no output schema, the description covers what the tool returns and the main filtering axes well enough to invoke it correctly. The gap is that limit and the numeric bounds of days are left entirely to the schema, with no hint of result-set size.

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 0%, so the description must compensate, and it only partly does: the example phrases convey the meaning of the time window and of ransomwareOnly ('ransomware-linked CVEs') and of vendor filtering. It never explains the limit parameter, the default values, or the 365-day maximum, and it even references 'product' while the schema only exposes vendor.

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 states a specific verb+resource: retrieving vulnerabilities CISA recently added to the Known Exploited Vulnerabilities catalog. It is clear and unambiguous, but it never mentions the sibling tool check_cves, so an agent gets no differentiation signal from the description itself.

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 gives explicit trigger conditions with three concrete natural-language user phrasings ('new KEV entries this week', 'exploited Microsoft vulnerabilities this month', 'ransomware-linked CVEs'), which map directly onto the days/vendor/ransomwareOnly parameters. However, it offers no when-not-to-use guidance and does not contrast itself with check_cves.

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