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

Beyond annotations (which already cover readOnly, idempotent, openWorld, non-destructive), the description adds the OSV data source, a batch ceiling of 500 entries, and the returned fields (severity, fixed versions). The credit cost (2) is useful operational context. Missing is any note on error behavior or what is returned for unknown packages.

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 dense sentence with the core purpose and data source front-loaded, followed by input modes, output fields, and cost. No filler, though the parenthetical nesting makes it slightly crammed.

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 4-parameter tool with no required params and no output schema, the description covers purpose, batch limits, and return fields. It leaves unresolved which parameter combination to use (name/version/ecosystem vs packages) and the array-item type discrepancy, which an agent would need to resolve before calling.

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 descriptions are near-tautological ('string', 'array or text'), so the description does the real work by spelling out the batch format (array of objects or 'name@version' per line) and the single-package mode. However, the description describes array items as {ecosystem,name,version} objects while the schema types them as strings, creating a mild inconsistency an agent must resolve.

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 resource and verb: known vulnerabilities from OSV for a package@version or a batch list, with severity and fixed versions. This clearly distinguishes it from a general metadata lookup like package_info, though it does not name that sibling 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?

Usage is implied by the phrasing ('for a package@version or a list of up to 500'), which effectively hints at a single-package mode and a batch mode. There is no explicit when-to-use/when-not guidance, no mention of when to prefer package_info, and no statement about what happens when version is omitted.

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