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

Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already establish a safe read-only scan, but the description adds critical behavioral context: it is a composite call that fans out to multiple services, partial failures degrade gracefully, bundlephobia's first measurement can take 5-30 seconds, and sources_failed reports timeouts. This rich transparency is exactly what an agent needs to manage timeouts and partial results.

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 efficient, packing purpose, usage, output shape, ecosystem scope, performance caveat, and error handling into a compact paragraph. Every sentence adds unique, actionable information; there is no fluff. It front-loads the core purpose and gets to usage guidance immediately.

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 (multi-source composite, external APIs, no output schema), the description is exemplary. It explicitly lists the summary fields, per-advisory details, links, and alternative versions — fully covering return values without an output schema. It also explains ecosystem limitations, timeout behavior, and partial-failure semantics, making it complete for an agent to judge outcome and formulate fallbacks.

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 coverage is 100% — both 'package' and 'version' have detailed descriptions covering scoped packages, examples, and default behavior. The description does not add new parameter-level semantics beyond the schema; it merely repeats the default-to-latest and scoped-package idea in its output block. Per policy, high schema coverage yields a baseline of 3, and the description doesn't elevate it.

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 opens with a clear, specific verb+resource: "Composite 'should I add this npm package to my project' check in ONE call — fans out across deps.dev ... and bundlephobia." It explicitly names the external services and the exact decision it supports, distinguishing it from sibling tools like scan_competitor_ai_presence. The NPM-only scope in v1 further sharpens the purpose.

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?

"Use whenever an agent asks 'is X safe / popular / small' or 'what does adding lodash cost me'" provides explicit trigger scenarios. It also gives an explicit exclusion: "PyPI / Maven / Cargo / Go fall under deps.dev:version directly," telling the agent when not to use this tool. This goes beyond typical one-line usage advice.

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