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

Goes well past the annotations (which only cover read-only/idempotent safety) by disclosing the 120-day window, the 20-advisories-per-package cap, newest-first ordering, and the zero-advisory case returning total 0. It also describes the payload fields (vulnerable ranges, fixed versions, exploitability conditions), which matters since there is no output schema.

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?

Four sentences, each doing distinct work: purpose, invocation contract, return shape, sibling routing. Front-loaded and free of filler despite the density of 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?

With no output schema, the description compensates by describing exactly what comes back per package and how to act on it. An agent has everything needed to call it correctly and interpret the result without further exploration.

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% and already documents the array, 1-50 bounds and the name pattern, so the description supplements rather than carries the burden. It still adds real meaning by stressing "names only, never versions" and telling the agent to compare returned ranges against its lockfile.

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?

Opens with a specific verb and resource ("Check npm packages for security advisories") and immediately distinguishes itself from siblings by naming get_advisory and latest_safe as different scopes. The scope (batch of package names, not versions) 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?

Explicitly states when to call it ("Start here before installing, upgrading or deploying") and routes to the correct alternatives for adjacent needs: get_advisory for a single advisory in full, latest_safe for the upgrade target. No inference required.

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