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

Beyond the readOnly/idempotent annotations, the description discloses partial failure handling (bundlephobia first measurement 5-30s, sources_failed listing timeouts), the exact output structure (summary fields, per-advisory detail, links, alternatives), and the NPM v1 restriction. This significantly enriches what annotations alone 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?

The description is front-loaded with a clear purpose, then efficiently packs usage, ecosystem scope, output fields, and failure behavior into three dense sentences with no filler. Every clause earns its place.

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?

For a complex composite tool with no output schema, the description covers the return values (summary block list), timing, failure degradation, and scope. Sibling tools and annotations fill the remaining context, making this sufficient for an agent to call correctly.

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 already describes both parameters with 100% coverage (package accepts scoped names, version defaults to latest). The description does not add syntax or format details beyond 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 a specific composite check verb 'should I add this npm package' and explicitly names the two services it fans out across (deps.dev, bundlephobia), distinguishing it from sibling tools. It clearly identifies the tool as a one-call advisory for npm packages.

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 instructs when to use: whenever an agent asks 'is X safe/popular/small' or 'what does adding lodash cost me', and states the alternative for other ecosystems ('PyPI/Maven/Cargo/Go fall under deps.dev:version directly'). This gives clear invocation context and exclusion.

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