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

Annotations already declare the operation as read-only, idempotent, and non-destructive. The description adds valuable behavioral context beyond this: partial failures degrade gracefully, the first bundlephobia measurement can take 5-30s, and sources_failed will list timeouts while still returning other data. This is exactly the kind of disclosure that helps an agent anticipate real-world 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 longer than minimal, but every sentence adds meaningful information: purpose, use case, return payload, ecosystem scope, and failure handling. It is front-loaded with the main purpose and organized logically, though slightly verbose.

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 must convey return values and runtime behavior, and it does. It enumerates the summary block fields, per-advisory details, links, and alternative version list. It also covers latency, partial failure, and scope limitations, making it complete for a tool of this complexity.

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 schema covers both parameters with descriptions (package name, scoped packages accepted; version defaults to latest), providing 100% coverage. The description adds no new parameter-level semantics beyond restating the package concept and the version default, so it does not elevate beyond the baseline.

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 identifies the tool as a composite 'should I add this npm package' check that fans out across deps.dev and bundlephobia. It specifies a concrete purpose (evaluating package safety, size, and cost) and distinguishes it from sibling tools by its npm-specific scope and aggregated multi-source output.

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?

The description explicitly states when to use the tool: whenever an agent asks if a package is safe, popular, or small, or what adding it costs. It also provides an exclusion criterion, noting that non-npm ecosystems (PyPI, Maven, etc.) should use deps.dev:version directly, which effectively names the alternative.

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