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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond that: it queries OSV.dev, aggregates multiple advisory sources, and discloses the cost and free-tier limit. No contradiction with annotations.

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, all useful and front-loaded: purpose and output, data source, then usage pattern and cost. There is no fluff or repetition of schema/annotation details.

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?

The description covers the main invocation mode, output contents, external source, and rate/cost behavior even though there is no output schema. It does not explicitly address empty results, error behavior, or when to prefer name/version vs packages, but an agent has enough information to call the tool correctly.

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%, so the description carries the burden, and it compensates well by defining the 'ecosystem:name@version' format, the 50-package max, and the supported ecosystems. The individual name/version/ecosystem fields remain implicit, but the single-package usage is inferable from the opening sentence.

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?

The description states a specific operation: checking for known security vulnerabilities in a package version. It enumerates supported ecosystems and the exact output fields (severity, CVE/GHSA IDs, fixing version), clearly distinguishing this tool from sibling data tools like package_info or price.

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?

It explicitly explains the batch usage pattern: pass up to 50 packages as 'ecosystem:name@version' to audit a lockfile, and identifies the OSV.dev data source. It does not explicitly mention when not to use the tool or name a sibling alternative, so it misses the top score.

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