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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description goes beyond them by disclosing the 20-package limit, the OSV.dev upstream dependency, the shape of the returned advisories, and the billing rules (paid via x402; invalid input or unreachable OSV.dev is not charged). It doesn't mention rate limits, timeouts, or partial-failure behavior, so it doesn't quite reach 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?

Two sentences, front-loaded with the core purpose first and billing last. Every sentence carries information (ecosystems, limits, return fields, pricing), though the ecosystem enumeration and the billing sentence add length; it is still well under the point of 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?

There is no output schema, and the description compensates by summarizing the return payload (advisory, CVE IDs, severity, CVSS, fixed versions, smallest safe upgrade, links). Combined with annotations and 100% schema coverage, it covers what an agent needs to call it, with only the single-package vs. batch input mode left implicit.

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 100%, so per-parameter documentation already exists; the description adds some meaning by stating the batch cap of 20 packages (the schema's maxItems of 1000 does not convey that), listing ecosystems, and giving the purl format. But it doesn't clarify the mutually exclusive single-package mode (name/version/ecosystem) versus the `packages` array, so it adds only modest value beyond the schema. Functional result: 3.5; reported as 3.

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 ("Check dependencies for known vulnerabilities") plus the resource (packages across npm/PyPI/Go/Maven/etc.), names the data source (OSV.dev), and enumerates what comes back (CVE IDs, severity, CVSS, fixed versions, smallest safe upgrade). This is clearly distinguishable from every sibling tool (token_safety_check, check_site_safety, etc.), which are about tokens, sites, or wallets rather than package dependencies.

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?

Explicitly gives a trigger context: "before installing or shipping", which tells the agent when this tool is appropriate. It also names list_prices as the pricing reference and states the billing exception (no charge for invalid input or if OSV.dev is unreachable). It does not name an alternative tool or a when-not-to-use condition, so it falls short of full 5-level routing guidance.

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