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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds material context beyond them: exact price ($0.001 USDC per call), bounded traversal in published order, static-registry-only constraint, an explicit 'what this cannot see' list, and byte-identical equivalence to a GET endpoint. This is unusually complete behavioral disclosure.

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?

Front-loaded with the core value proposition and every sentence carries information (scope, roll-up factors, exclusions, cost, endpoint equivalence). It is longer than typical but dense rather than padded, with only minor compression possible.

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?

An output schema exists so return structure need not be described, and the description already states that per-dependency rows, counts, a verdict line, and an exclusion list are returned. Cost, scope boundaries, and limitations are all covered, leaving nothing an agent needs missing.

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?

Only one parameter and schema coverage is 100%, so the schema already documents the name input. The description's 'optionally scoped' note merely restates what the schema says, adding no new syntax or format guidance.

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?

States a specific verb (reads the package and each direct dependency) and resource (npm registry metadata) with explicit scope, then names exactly what it rolls up (install scripts, deprecation, provenance, maintainer/publish age). It is clearly distinguishable from the sibling market_npm_package_risk because it operates on direct dependencies rather than a single package.

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?

Gives clear usage context ('one paid call', static metadata only) and a strong exclusion list: no lockfile resolution, no transitive walk, no download/execute, no typo comparison. The only gap is that it never names the sibling tool to use for those excluded cases, so the agent must infer routing.

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