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

Even with annotations declaring read-only/idempotent behavior, the description adds critical behavioral context: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, and sources_failed field indicates timeouts. This goes well beyond the annotation flags.

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?

Every sentence is dense with information: purpose, external sources, use cases, ecosystem scope, return block, and failure behavior. It's front-loaded with the main purpose and flows logically to limitations, with no wasted words.

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 enumerates the exact summary fields (is_latest, license, bundle sizes, etc.), additional outputs (advisories, links, alternative versions), and explains the non-npm fallback. It also discloses timing and partial failure behavior, making it fully self-contained for an agent.

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 already has 100% coverage with descriptions for both parameters (package and version). The description does not add extra parameter-level meaning; it only mentions version in the context of output fields, not as additional guidance. Therefore baseline 3 is appropriate.

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 the composite check purpose: 'should I add this npm package to my project' in ONE call, and it names specific sources (deps.dev and bundlephobia) and outputs. This distinguishes it from sibling tools, none of which are dependency scanners.

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 tells when to use: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. It also provides an exclusion: 'PyPI / Maven / Cargo / Go fall under deps.dev:version directly', guiding the agent away from this tool for non-npm ecosystems.

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