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

Annotations already declare readOnlyHint, idempotentHint, etc. The description adds rich behavioral context: fans out to two services, returns specific fields (summary block, per-advisory detail, links, alternative versions), mentions timing (bundlephobia first measurement takes 5-30s), and explains graceful degradation (sources_failed will list timeout, rest still returns). No contradictions 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 a single paragraph that packs a lot of information. It is front-loaded with the core purpose. While dense, every sentence serves a purpose (use case, return structure, ecosystem scope, timing caveat). Slightly long but justified by the tool's complexity; could be shorter but acceptable.

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 check, two services, multiple return types, partial failures, ecosystem limitation) and absence of an output schema, the description covers all necessary aspects: what is returned (fields, advisories, links, alternatives), timing, graceful degradation, and ecosystem scope. It is fully complete for an agent to use correctly.

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 covers package and version with 100% description. The description adds value by noting that scoped packages (e.g., @types/node) are accepted for the 'package' parameter, which is not explicit in the schema. It also reinforces version defaults. Overall, it clarifies acceptable inputs beyond 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 is a composite check for npm packages combining deps.dev and bundlephobia, with a specific verb ('scan') and resource ('dependency'). It distinguishes from sibling tools by specifying the npm ecosystem and the exact use case ('should I add this npm package?'). The function is unique among siblings, which include generic research 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?

Explicitly states when to use: 'whenever an agent asks is X safe / popular / small' and gives a concrete example ('what does adding lodash cost me'). Also tells when not to use: 'PyPI / Maven / Cargo / Go fall under deps.dev:version directly'. Provides guidance on partial failures and timing.

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