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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds significant behavioral context beyond these: the composite fan-out nature, graceful degradation on partial failures, the 5-30s first-measurement delay for bundlephobia, and the sources_failed field in case of timeouts. This fully discloses expected behavior.

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 front-loaded with purpose, then usage, return summary, ecosystem constraints, and failure behavior. Every sentence contributes unique information, and despite being moderately long, it is efficiently organized for a composite tool with multiple sources and edge cases. No filler or redundancy.

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 fully compensates by enumerating the return summary fields (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable), per-advisory detail, links, and recent alternative versions. It also covers ecosystem limitations and timeout behavior, making the tool's usage and expected output completely clear.

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 for parameters is 100%, with both 'package' and 'version' fully described in the schema (npm package name, scoped packages accepted, version defaulting to latest). The description adds no substantial semantic value beyond the schema, merely reiterating the schema's own explanation. 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 clearly defines the tool's purpose: a composite 'should I add this npm package to my project' check that fans out across deps.dev and bundlephobia. It specifies the exact resources inspected (license, advisories, version history, bundle size, dependency count, ESM/tree-shake support) and is easily distinguishable from sibling tools, none of which perform dependency scanning.

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 guidance is given: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. It also provides an exclusion with an alternative: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly'. This clearly states when to use and when not to use the tool.

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