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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructiveHint. The description adds behavioral details beyond those: partial failure degradation, bundlephobia's first measurement taking 5-30s, sources_failed indicating timeouts while other data still returns. It also discloses the return summary block fields, making behavior predictable without contradicting 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 well-structured: starts with the core purpose, then usage triggers, return format, ecosystem scope, and failure behavior. Though it's longer than a simple tool description, each sentence adds distinct value and the format is front-loaded. No filler or redundancy.

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 enumerates the exact summary fields (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable) plus per-advisory detail and alternative versions. It covers edge cases like timeouts and partial failures, and specifies the ecosystem limitation. For a composite tool with two external sources, this 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%, so both 'package' and 'version' are already documented. The description adds meaning by stating the 'package' param expects npm package names and mentions scoped packages are accepted. It also clarifies version defaults to latest when omitted, echoing the schema but reinforcing the semantic. Since the baseline for high schema coverage is 3, the added param context raises it to 4.

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 states a specific composite action: 'should I add this npm package to my project' check, listing the two data sources and what each contributes. It distinguishes itself from siblings like validate_claim and scan_competitor_ai_presence by explicitly scoping to npm dependency evaluation with license/advisory/version/bundle information.

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?

Provides explicit trigger phrases: 'is X safe / popular / small' or 'what does adding lodash cost me'. Also gives an exclusion: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly', steering users to an alternative path. This is strong when-to-use and when-not-to-use guidance.

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