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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds critical behavioral details: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30 seconds, and sources_failed lists timeouts while the rest still returns. This goes beyond 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?

The description is multi-sentence but every sentence adds value: first sentence defines purpose, second gives usage examples, third details return format, fourth states ecosystem limitation and failure handling. No wasted words. Well-structured and front-loaded.

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?

Given the tool is a composite with multiple data sources, the description covers all key aspects: what it checks (license, advisories, version history, bundle size, ESM/tree-shake), return content, partial failure behavior, ecosystem scope, and limitations. No output schema exists, so description fully describes returns.

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. The description adds extra context: scoped packages (e.g., '@types/node') are accepted for 'package', and 'version' defaults to latest when omitted. This adds meaningful nuance beyond the schema descriptions.

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 clearly states it's a composite check for 'should I add this npm package' covering license, advisories, version history, and bundle info. It uses a specific verb ('scan') and resource ('dependency') and distinguishes from siblings by focusing on npm packages, while other siblings are unrelated.

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 to use when an agent asks about safety, popularity, size, or cost of adding a package. Also specifies limitations: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly.' This provides clear context for when not to use.

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