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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint true. The description adds valuable behavioral details: it fans out to multiple external services, returns a structured summary block with specific fields, lists per-advisory detail, links, and alternative versions. It transparently warns about bundlephobia's first measurement taking 5-30s and that sources_failed will list timeouts. No contradictions with annotations.

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 relatively long but well-structured: a clear purpose statement upfront, followed by usage context, return detail, ecosystem scope, and edge-case behavior. Every sentence adds value, though a minor trim could tighten it slightly without losing information.

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 bears full responsibility for explaining returns. It does so thoroughly: a summary block with specific fields (is_latest, license, etc.), per-advisory detail, links, and alternative versions. It also covers partial failures and timing. For a tool of moderate complexity (composite call, multiple sources), this is complete and sufficient.

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 description coverage is 100% with both package and version documented. The description does not add new parameter-level information beyond what the schema provides (e.g., 'Scoped packages accepted', 'defaults to latest'). Since the schema already covers parameter meanings, the description adds no incremental semantic value for parameters, resulting in a baseline score of 3.

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 and specific verb-resource: 'Composite should I add this npm package to my project check in ONE call'. It explicitly states the tool fans out across deps.dev and bundlephobia for npm packages, distinguishing it from sibling tools that are either for other ecosystems or different queries.

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 provides explicit when-to-use guidance: 'Use whenever an agent asks is X safe / popular / small or what does adding lodash cost me'. It also notes limitations—'NPM ecosystem only in v1'—and mentions fallback via deps.dev directly for other ecosystems, plus handling of partial failures.

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