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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the bar is lower, yet the description adds real context: the upstream data sources, that CVE lookups also surface NVD's record, and the per-call price of $0.005. It does not cover latency, caching or how ambiguous package/version input is handled, which is the main remaining gap.

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 question and scope are front-loaded in the first sentence, followed by sources and the pricing note. The sentence about being 'built for coding agents and for developers who want a sourced answer instead of a scanner setup' is somewhat promotional but still conveys positioning; overall little waste.

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 still tells the agent what answers come back (vulnerability status, in-the-wild exploitation, recommended safe version) and which catalogs back them. Only error or no-match behavior is left unstated, which is minor for a read-only lookup.

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% and already gives examples including Maven group:artifact and Go module paths, so the baseline is 3. The description goes beyond it by enumerating the accepted ecosystem names (npm, PyPI, Maven, Go, crates.io, NuGet, RubyGems, Packagist) and by framing name/version/ecosystem as mutually exclusive with vulnerabilityId.

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?

Opens with a concrete question set (is it vulnerable, is it exploited in the wild, what is the safe upgrade) and names the resource, the sources (OSV.dev, CISA KEV, NVD) and the supported ecosystems. It also distinguishes the two modes, package check vs single CVE/GHSA id, so an agent knows exactly what the call does without opening the schema.

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 description makes the two invocation modes explicit ('One call answers it for npm, ... or for one CVE/GHSA id') and positions itself against the alternative of setting up a scanner. It stops short of explicit when-not guidance or stating prerequisites such as which ecosystems need a version supplied.

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