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

Beyond the readOnly and idempotent annotations, the description discloses partial failure behavior (bundlephobia timeout, sources_failed), latency (5-30s first measurement), and the composite fan-out across two services. This gives the agent important expectations about performance and failure handling.

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 multi-sentence but well-structured, front-loading the core purpose and usage, then adding return details, ecosystem scope, and failure behavior. It's longer than strictly necessary but each sentence carries unique value.

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?

Without an output schema, the description lists all key return fields (summary block, per-advisory detail, links, alternative versions) and explains the degraded behavior on failure. Combined with annotations, the agent has a full picture of what happens when the tool is called.

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?

The input schema already has 100% coverage for both parameters, describing package name and version defaults. The description adds minimal parameter-specific detail; the mention of 'new version' latency is more behavioral than semantic. Thus, a 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 this is a composite check for whether to add an npm package, listing specific data sources (deps.dev, bundlephobia). It distinguishes itself by specifying the npm ecosystem scope and alternative handling for other ecosystems, though it doesn't name a specific sibling tool.

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...' and gives concrete examples ('is X safe / popular / small'). It also states exclusions: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly,' guiding users to alternatives.

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