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

Annotations already mark this as read-only, idempotent, open-world, and non-destructive. The description adds extra behavioral details: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, and sources_failed will list it if it times out. This goes well beyond the safety profile provided by annotations, helping the agent set expectations and handle delays.

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 dense but well-structured. It leads with the core purpose, then usage guidance, return contents, ecosystem scope, and failure behavior. Every sentence adds value; despite its length, it avoids redundancy and remains thoroughly readable. The format allows quick scanning of the most critical 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?

Given the tool's complexity (two external data sources, multiple output categories, partial-failure behavior), the description covers all essential aspects: what it returns (summary block, per-advisory detail, links, alternatives), the NPM-only limitation, and failure handling. No output schema exists, so the description carries the full burden of explaining outputs, and it does so thoroughly.

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?

The input schema already documents both parameters (package and version) with descriptions, achieving 100% schema coverage. The description does not add additional parameter-level semantics beyond what the schema provides; it only mentions them implicitly in the context of usage. For a schema with full coverage, a baseline score of 3 is appropriate, as the schema does the heavy lifting.

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 this is a composite 'should I add this npm package' check that fans out to deps.dev and bundlephobia. It explicitly lists the categories of information gathered (license, advisories, version history, bundle size, dependency count, ESM/tree-shake support), making the tool's purpose unmistakable and distinguished from any sibling tool for dependency analysis. The resource (npm package) and action (scan) are specific and concrete.

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?

The description gives explicit guidance: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me".' It also states an exclusion: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly.' This provides exactly the type of when-to-use and alternative guidance needed, including what not to use it for.

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