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

Annotations indicate read-only, open-world, idempotent. The description adds significant detail: fans out to two external services, bundlephobia first measurement may take 5-30s, partial failures degrade gracefully, and sources_failed field is mentioned. No contradiction with 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 dense but well-structured, front-loading the purpose. Every sentence adds value, though it could be slightly more concise. It efficiently conveys complex behavior without 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?

No output schema exists, yet the description thoroughly lists the return fields (summary block, per-advisory detail, links, recent versions). It also covers error scenarios (sources_failed for timeouts). All necessary context is provided.

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?

Both parameters are described in the schema. The description adds meaning: clarifies that version defaults to latest, shows example format for scoped packages ('@types/node'), and explains the context of each parameter.

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 performs a composite check for npm packages, combining deps.dev and bundlephobia data. It lists specific checks: license, advisories, version history, bundle size, etc. This distinguishes it from sibling tools, none of which appear to be 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?

It explicitly says when to use: 'is X safe / popular / small' or 'what does adding lodash cost me'. It also specifies limitations: NPM only in v1, with alternatives listed for other ecosystems. Partial failure handling is described, giving clear guidance on expected behavior.

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