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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive. The description adds behavioral details beyond annotations: it fans out across two services, partial failures degrade gracefully, and bundlephobia's first measurement can take 5-30 seconds. This provides useful context for the agent.

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 dense paragraph that packs substantial information without unnecessary words. It could benefit from slight structuring (e.g., bullet points), but it remains concise and front-loaded with the core purpose.

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?

Despite no output schema, the description thoroughly lists return fields (summary block, per-advisory detail, links, alternative versions) and explains error handling. Given the tool's complexity (two sources, partial failures), the description is complete and leaves no critical gaps.

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 description coverage is 100% — both 'package' and 'version' have descriptions in the schema. The description adds minor context (defaults to latest version, scoped packages accepted), but does not significantly go beyond what the schema already provides. Baseline 3 is appropriate.

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 check for npm packages, combining deps.dev (license, advisories, version history) and bundlephobia (bundle size, dependencies, ESM support). It distinguishes from siblings like 'deep_research' or 'scan_competitor_ai_presence' by being specific to npm dependency 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?

Explicitly says 'Use whenever an agent asks is X safe / popular / small or what does adding lodash cost me'. Also notes limitations: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly', guiding when not to use this tool.

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