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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds valuable runtime behavior: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, and sources_failed will list if it times out. This goes beyond annotations, though it doesn't cover every possible edge (e.g., rate limits), which is acceptable.

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?

A dense paragraph but every sentence contributes: purpose, use case, return fields, ecosystem scope, and failure behavior. Slightly long for a tool description, but justified given the composite nature and multiple data sources. No 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, so the description correctly documents the return shape, including the summary block fields, per-advisory details, links, and alternative versions. It also covers edge cases like timeouts, partial failures, and ecosystem limitations. Complete for a complex composite tool.

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 both parameters with descriptions (100% coverage), including scoped package acceptance and defaulting behavior. The description doesn't add new parameter-level details beyond the schema, but it does frame the parameters within the composite use case. Baseline 3 is appropriate since the schema already handles the burden.

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 identifies this as a composite npm-package evaluation tool, with specific verbs like 'check' and 'fans out', and a concrete use case ('should I add this npm package'). It distinguishes itself from sibling tools by explicitly scoping to NPM and naming deps.dev:version as the alternative for other ecosystems.

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?

Provides explicit when-to-use guidance with concrete examples ('is X safe / popular / small', 'what does adding lodash cost me'), and an explicit alternative: 'PyPI / Maven / Cargo / Go fall under deps.dev:version directly'. Also clearly notes the NPM-only scope in v1.

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