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

Annotations mark it as read-only and non-destructive, and the description adds valuable behavioral context: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, and sources_failed will list timeouts. This exceeds what annotations alone provide, though it doesn't detail all possible failure modes or rate limits.

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 moderately long but every sentence serves a purpose: purpose, use cases, return fields, ecosystem limitation, and failure behavior. It is well-structured and front-loaded with the core purpose, though slightly dense and could be tightened.

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?

For a tool with no output schema, the description thoroughly explains the return block, failure modes, and limitations. It covers what an agent needs to know about performance and scope. Minor gaps like exact link structure or per-advisory detail do not undermine completeness.

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 'package' and 'version', so the schema handles parameter semantics. The description reinforces default behavior and scoped package support but does not add new parameter-level detail beyond the schema.

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 it's a composite 'should I add this npm package to my project' check in ONE call, detailing the data sources (deps.dev and bundlephobia) and output fields. It distinguishes itself from sibling tools by focusing specifically on npm package evaluation.

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 explicitly states when to use the tool: for questions like 'is X safe / popular / small' or 'what does adding lodash cost me'. It also gives a clear exclusion and alternative: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly.'

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