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

With no annotations, the description carries the full burden and does disclose several real traits: the upstream source (OSV), a credit cost, a hard batch ceiling of 500, and the shape of the results (severity, fixed versions). It omits error behaviour for unknown packages/ecosystems, whether the batch is atomic, and any rate/throughput limits.

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 front-loaded sentence that packs the resource, both input modes, the batch limit, the return shape and the cost with no filler. It is dense and nested to the point of being slightly hard to parse on first read, which is the only thing keeping it off a 5.

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 lookup with four optional parameters, no output schema and no annotations, the description supplies source, scope, batch cap, cost and return fields — enough to call it correctly. The one real gap is how name/version/ecosystem combine with packages when both are supplied, which an agent must guess.

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 schema's own parameter descriptions are placeholders ("string", "array or text"), so the description is the only place the two invocation modes are explained — single {ecosystem,name,version} versus a list of up to 500 entries supplied either as objects or as newline-delimited "name@version" text. That is genuine meaning added beyond the structured fields.

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?

"Known vulnerabilities (OSV) for a package@version" names the resource and the data source, which is enough to distinguish it from the nearest sibling (package_info, which describes rather than audits a package). It stops short of explicitly contrasting with that sibling, but the verb+scope is unambiguous.

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 two supported input shapes (single package vs. batch list of up to 500) imply when the tool applies, and the 2-credit note signals it is a paid call worth batching. There is no explicit guidance on when to prefer this over package_info or what to do on partial failures, so usage context is only implied.

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