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

Annotations declare readOnly, openWorld, idempotent, non-destructive, and the description adds critical behavioral details: fan-out across two services, the 5-30s first measurement delay for bundlephobia, and that partial failures still return results with sources_failed. This goes beyond the annotations to set agent expectations about latency and failure handling.

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 a single dense paragraph that front-loads the core purpose first, then immediately gives usage guidance, return contents, and limitations. Each sentence adds distinct value—no filler—while remaining compact given the tool's composite nature.

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?

There is no output schema, so the description carries the full burden of explaining return values, and it enumerates the summary block fields (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable) plus per-advisory detail and version alternatives. It also covers ecosystem scope, timing behavior, and failure semantics, making the tool fully understandable without further lookups.

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?

Input schema already documents both parameters with clear descriptions (package name, version defaulting to latest). Description reinforces the default behavior ('Defaults to the latest published version') and mentions scoped-package support ('@types/node') that's already in the schema, but doesn't add substantial new parameter semantics beyond the existing 100% coverage.

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 opens with a clear verb phrase: 'Composite "should I add this npm package to my project" check in ONE call' and immediately identifies the two data sources (deps.dev and bundlephobia). It explicitly scopes to NPM ecosystem in v1 and points to an alternative for other ecosystems, distinguishing it from general dependency tools.

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?

Explicit use-case trigger: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me".' It also provides an exclusion/alternative: 'PyPI / Maven / Cargo / Go fall under deps.dev:version directly,' and explains when to expect the alternative. It also describes graceful degradation context, further guiding the agent on what to expect.

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