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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds crucial context beyond that: the composite fan-out across two external services, graceful degradation on partial failures, the 5-30s first-measurement delay from bundlephobia, and the sources_failed field listing timeouts. This gives the agent realistic expectations about latency and failure modes.

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 information-dense but well-structured: purpose first, then when-to-use, then return shape, then ecosystem scope, then failure behavior. It is longer than strictly necessary but every sentence carries useful content. The front-loading of the core purpose and the clear list of fields make it easy to scan.

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?

With no output schema, the description compensates by listing the exact summary fields, per-advisory details, links, and alternative versions. It also covers the NPM-only limitation and partial failure behavior. Missing elements like invalid-package error handling are minor for a tool of this complexity. The provided context is sufficient for an agent to understand what results to expect.

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% with clear descriptions for both parameters (package and version). The description reinforces the meaning by giving examples like 'adding lodash' and mentioning scoped packages in the schema. Since the schema already fully documents the parameters, the description adds no new semantic information, 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 opens with a specific verb and resource: a composite 'should I add this npm package' check, naming the exact data sources (deps.dev and bundlephobia) and the fields returned. This clearly distinguishes it from sibling tools, which are either broader research tools or unrelated network/prediction 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?

Explicit usage trigger: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. Also provides a clear exclusion: NPM-only in v1, with non-NPM ecosystems delegated to deps.dev:version directly. This tells the agent both when to use and 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.