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

The description adds material behavioral context beyond the readOnlyHint/idempotentHint annotations: it discloses the composite fan-out, the 5-30s latency on first bundlephobia measurement, the graceful degradation with sources_failed, and the guarantee that the rest still returns. This is exactly the kind of operational nuance the annotation fields cannot 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 dense but well-structured: it front-loads the core purpose, then usage, then limitations and failure semantics. Every sentence adds information, though the final sentence is somewhat long and could be split for easier parsing. It earns a 4 for being efficient yet thorough.

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 compensates by enumerating the returned summary fields (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable) and noting per-advisory detail, links, and recent alternatives. It also covers edge cases (timeouts, partial failures) and ecosystem limitations, making it fully complete for a composite health-check 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 both 'package' and 'version' having clear descriptions. The tool description restates the npm-specific nature and default version behavior already in the schema, adding no new parameter-level details. Per the rubric, baseline 3 is appropriate when the schema carries the semantic load.

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, verb-driven purpose: a composite 'should I add this npm package to my project' check. It names the exact sources (deps.dev and bundlephobia) and the data categories (license, advisories, bundle size, ESM support), making the tool's scope unmistakable and distinct from siblings like deep_research or validate_claim.

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?

Usage guidance is explicit: 'Use whenever an agent asks is X safe / popular / small or what does adding lodash cost me.' It also states a clear exclusion ('NPM ecosystem only in v1') and points to a direct alternative ('deps.dev:version directly') for other ecosystems, even naming the fallback behavior.

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