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

Annotations already declare read-only/idempotent/open-world, but the description adds information they cannot convey: cost ($0.002 per call, 10 free/day), the payment-required result path with x402 options, and that invalid-input or upstream-failure errors return isError and are not charged. That is exactly the kind of operational context an agent needs before spending money on a call.

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?

Front-loads the resource and return fields, then usage, then cost and error semantics — a sensible order with no filler. It is a single dense block, and the pricing/error sentence is long, but every clause conveys operative information.

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, open-world lookup with an output schema, the description covers what an agent still needs: supported ecosystems, batch limits, cost, free tier, payment behavior, and error/charging semantics. Return-value shape is handled by the output schema, so nothing material is missing.

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%, so the baseline is 3, and the description adds real meaning on top: it explains that packages takes combined 'ecosystem:name@version' strings and that this form is for lockfile auditing, clarifying the relationship between the batches and the single name/version/ecosystem fields. It stops short of stating whether name+version and packages may be combined or which is required, so not a 5.

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+resource (look up known security vulnerabilities for a package version) and immediately scopes it with supported ecosystems and returned fields (severity, CVE/GHSA ids, fixed version). It also names the data source (OSV.dev) and distinguishes itself from package_info, which covers general package facts.

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 says 'When to use: For CVEs in one package version' and routes the general-facts case to package_info, naming the sibling server. It adds a second concrete use mode (batch audit of a lockfile via up to 50 'ecosystem:name@version' entries), so the agent knows both when and how.

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