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

The description adds substantial behavioral context beyond the annotations: it explains the composite nature of the call, the partial failure behavior with sources_failed listing timeouts, and the latency characteristic of bundlephobia's first measurement on a new version (5-30s). This is exactly the kind of operational detail that an agent needs to set expectations and interpret results. The description is consistent with the readOnlyHint, openWorldHint, and idempotentHint annotations, with no contradictions.

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 long but every sentence contributes meaningful information: purpose, use cases, return structure, ecosystem limitation, and failure behavior. It is front-loaded with the core purpose and uses a logical flow from what it does, to when to use it, to what it returns, to caveats. No wasted words.

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?

Without an output schema, the description fully enumerates the return shape (summary block with specific fields, per-advisory details, links, alternative versions). It also addresses the main edge cases: non-NPM ecosystems, partial failures, and slow first measurements. For a composite tool of this complexity, the description is remarkably complete and self-contained.

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 provides 100% coverage for both parameters (package and version) with clear descriptions, so the baseline is 3. The description adds minimal extra parameter semantics; it only implies that the package is an npm package and that versions can be checked in the context of bundlephobia timing. Since the schema carries the full semantic weight, the description does not need to compensate.

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 states a clear, specific purpose: a composite check for 'should I add this npm package to my project' that fans out across deps.dev and bundlephobia. It explicitly enumerates what each source contributes (license, advisories, version history, bundle size, dependency count, ESM/tree-shake support), which distinguishes it from an abstract or vague 'scan' tool. It also differentiates from potential alternatives like deps.dev:version for other ecosystems.

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 usage guidance is provided: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me".' It also gives an exclusion criterion: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly,' which tells the agent exactly when not to use this tool and what to use instead. This is textbook when/when-not guidance.

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