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

The description discloses concrete behavioral traits beyond annotations: 'bundlephobia's first measurement on a new version can take 5-30s' and 'Partial failures degrade gracefully — sources_failed will list it if it times out, the rest still returns'. These latency and failure handling details are not present in the annotations, which already declare the operation read-only and idempotent. No contradiction with annotations exists.

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 six sentences long, each serving a distinct purpose: defining the composite operation, listing covered data sources, giving usage triggers, enumerating return fields, declaring ecosystem scope, and explaining failure behavior. Every sentence earns its place, and the main purpose is 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?

Given the tool's complexity (composite of two external services, no output schema), the description compensates fully by enumerating every returned field in the summary block, detailing partial failure and timeout behavior, and stating ecosystem limitations. An agent can correctly invoke the tool and interpret results without needing additional context.

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% with descriptions for both parameters, giving a baseline of 3. The description adds useful semantics: 'Scoped packages (e.g. "@types/node") are accepted' and 'Defaults to the latest published version when omitted', which clarify invocation specifics not fully captured in the schema. This meaningful addition justifies a score above baseline, though it is not extensive enough for 5.

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 'Composite should I add this npm package to my project check in ONE call', which precisely states the tool's purpose, resource, and composite nature. It distinguishes itself from siblings by explicitly limiting scope to the NPM ecosystem and naming the backend services (deps.dev and bundlephobia), which no other sibling tool appears to combine.

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?

It explicitly says 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"', giving clear invocation triggers. It also provides a direct exclusion: 'PyPI / Maven / Cargo / Go fall under deps.dev:version directly', pointing to an alternative 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.