search_cves

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

With no annotations, the description does the heavy lifting: it discloses result ordering ('most urgent first') and explains the two most consequential output fields, `exploited` (CISA KEV = attacked in the wild) and `epss` (0-1 probability of exploitation in 30 days). It does not mention NVD API rate limits, auth requirements, or what an empty result looks like, which keeps it short of 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?

Three sentences, front-loaded with the what, then the when with an example, then the return semantics. Every clause carries information; nothing is restated from the schema.

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 four-parameter search with no annotations and no output schema, the description covers purpose, trigger, ordering, and the two decision-relevant result fields. The remaining gap is that the rest of the result shape (CVE ID, severity, dates) and the effect of `limit` are left unstated.

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 only 25% (only `days` is documented in-schema), so the description must compensate. It adds real meaning for `keyword` (product/library/vendor, min length implied by example) and shows `days` in use, but says nothing about `limit` or `minSeverity`, leaving two of four parameters unexplained in both places.

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+resource+mechanism: keyword search over recent CVEs via the NVD API, with keyword scoped to product/library/vendor. It implicitly separates itself from get_cve (single lookup) and scan_lockfile by being a keyword-driven discovery search, though it never names those siblings explicitly.

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?

'Use to find new vulnerabilities affecting a stack, e.g. keyword 'laravel', days 30' gives a concrete triggering scenario and a worked example, which is well above implied usage. It lacks explicit when-not guidance or pointers to get_cve/check_package for single-package lookups.

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