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

Annotations already declare read-only, idempotent, and open-world behavior. The description adds significant context beyond that: it fans out across two external services, returns a specific summary block, and explicitly explains partial failure handling and potential timeout (5-30s for bundlephobia's first measurement). This gives the agent a clear picture of what to expect, with no contradiction.

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 well-structured: it opens with the core purpose, then gives usage triggers, return fields, ecosystem scope, and failure behavior. Every sentence carries useful information with no fluff or repetition, making it concise despite its length.

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?

Since there is no output schema, the description compensates by enumerating the summary block fields (is_latest, license, etc.) and other return elements like per-advisory detail and links. It also covers data sources, scope limitations, and partial failure modes. Given only 2 parameters and a complex composite behavior, the description is remarkably 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?

The input schema fully describes both parameters ('package' and 'version') with clear explanations, so schema coverage is 100%. The description does not add any additional parameter details beyond what the schema already provides, so the baseline of 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 "should I add this npm package to my project" check in ONE call' and specifically names the data sources (deps.dev and bundlephobia). It defines the resource as an npm package and the primary purpose as evaluating safety, popularity, and size, making it distinct from sibling research tools.

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 gives explicit use cases: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. It also offers a clear when-not-to-use by stating 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly'. However, it doesn't name a specific sibling tool as an alternative, only an external service.

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