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

The description goes beyond annotations by detailing fan-out behavior to two services, graceful degradation on partial failures, and a specific timing caveat ('bundlephobia's first measurement on a new version can take 5-30s'). There is no contradiction with the provided annotations (readOnly, idempotent, etc.).

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 information-dense but remains readable. Every sentence serves a purpose, covering use case, services queried, return structure, ecosystem scope, and failure behavior. It is slightly long but well-organized, justifying a 4 rather than 5.

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 no output schema, the description fully enumerates return fields (summary block with is_latest, license, etc.), per-advisory details, links, alternative versions, and a sources_failed indicator for graceful degradation. The tool has only 2 parameters with no nested objects, so this is complete.

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?

With 100% schema coverage, the baseline is 3. The description adds value by clarifying that version defaults to the latest when omitted and that scoped packages (e.g. '@types/node') are accepted, which supplements the schema descriptions. However, this added value is moderate, earning a 4.

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 tool is a composite check for evaluating npm packages, specifying the exact services queried (deps.dev and bundlephobia) and the type of information returned (license, advisories, bundle size, etc.). It uses a specific verb-resource pair ('Scan Dependency') and distinguishes itself from sibling tools by focusing on npm dependency analysis.

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: 'whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. It also provides clear guidance on ecosystem limitations ('NPM ecosystem only in v1') and directs users to alternative tooling for other ecosystems ('PyPI / Maven / Cargo / Go fall under deps.dev:version directly'). Additionally, it explains partial failure behavior gracefully.

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