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

Beyond the readOnly/idempotent annotations, the description discloses latency behavior ('bundlephobia's first measurement ... can take 5-30s'), partial failure degradation ('sources_failed will list it if it times out, the rest still returns'), and return structure. It also reveals the fan-out architecture across two services, which annotations alone don't convey.

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?

Every sentence carries functional value: purpose, usage, return fields, ecosystem scope, and error handling are all covered without redundancy. The dashes and semicolons create a scannable structure despite the density.

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 to lean on, the description fully inventories returned data (summary fields, advisory details, links, alternative versions). It covers ecosystem constraints, failure modes, and timeout behavior, making it a complete guide for an agent calling this tool.

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% with the package and version params already fully described. The description adds no new parameter-level detail—the ecosystem limitation and scoped-package support are already in the schema—so the baseline 3 is appropriate.

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 'Composite ... check in ONE call' and clearly specifies the resource (npm package) and the two data sources (deps.dev and bundlephobia). It distinguishes itself by noting 'NPM ecosystem only in v1' and pointing to deps.dev:version for other ecosystems, making its scope obvious.

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 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. Also gives an exclusion: for PyPI/Maven/Cargo/Go, fall under deps.dev:version directly. This provides clear when-to-use and when-not-to-use guidance.

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