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

The description adds valuable behavioral context beyond the annotations: it discloses graceful degradation under partial failures, the 5-30s timeout for bundlephobia's first measurement, and the presence of a 'sources_failed' field. Even with readOnlyHint/idempotentHint annotations, this timeout/failure behavior is not inferable from annotations alone, so the description carries its weight.

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 one-sentence purpose, then usage, then return fields, then caveats. It is dense but every sentence earns its place—no filler, no repetition of annotations or schema. The length is justified by the tool's composite nature and the numerous return fields and failure modes it discloses.

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?

Despite having no output schema, the description explicitly enumerates the summary block fields (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable), per-advisory details, links, and alternative versions. It also covers ecosystem scope and partial-failure behavior. For a tool this complex, the description is remarkably complete.

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%: both 'package' and 'version' are fully described in the schema, including the default behavior for version. The description adds little beyond that—the mention of 'version' is tied to the measurement timeout, not to parameter format or constraints. Baseline 3 is appropriate because the schema does the heavy lifting.

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 clear, specific verb+resource: "Composite 'should I add this npm package to my project' check in ONE call — fans out across deps.dev ... and bundlephobia." It states exactly what the tool does and its inputs (npm package), and the composite nature distinguishes it from sibling tools that focus on entity research or search, none of which handle dependency checks.

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 states when to use: "Use whenever an agent asks 'is X safe / popular / small' or 'what does adding lodash cost me'." It also provides an explicit exclusion: "NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly," telling agents when NOT to use this tool and pointing to an alternative. This is a model of usage guidance.

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