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

The description goes well beyond the annotations by explaining it fans out across external services, publishes a specific return shape, and discloses graceful degradation and timeout behavior: 'bundlephobia's first measurement on a new version can take 5-30s; sources_failed will list it if it times out'. It also notes the v1 scope limitation. No contradiction with the read-only/idempotent/harmless 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 structured with a clear opening sentence, then usage, output shape, ecosystem scope, and failure behavior. Each sentence contributes new, actionable information without fluff. It is longer than average but earns its length by covering critical operational details like latency and partial failures, making it well-organized and front-loaded.

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 listing the exact summary fields returned (is_latest, license, published_at, etc.), per-advisory details, links, and alternative versions. It also covers latency, timeout, and source failure behavior. For a composite tool across two external APIs, this is comprehensive enough for an agent to invoke it correctly and interpret responses.

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?

The input schema fully documents both parameters (package name, version) with examples and defaults, giving 100% coverage. The description adds context on use cases and output, but does not add new meaning to the parameters themselves. With baseline 3 for full schema coverage, the description provides slight extra context (e.g., scoped packages accepted) already covered by schema, so no higher score is justified.

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 composite purpose: 'should I add this npm package to my project' check, and explicitly names the data sources (deps.dev and bundlephobia) and what they provide. It clearly distinguishes itself from sibling tools by focusing on npm dependency risk/impact evaluation, a unique niche among the listed tools.

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 gives explicit usage triggers: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. It also clarifies ecosystem boundaries: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly', which steers the agent to alternative tools for non-npm packages.

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