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

The description goes far beyond the read-only hints in annotations by detailing the composite fan-out behavior across two services, the exact return payload (summary block, per-advisory detail, links, alternative versions), and the graceful degradation of partial failures. It also discloses the potential 5-30s delay for bundlephobia's first measurement, which is important operational knowledge absent from structured fields.

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 organized with the core purpose front-loaded, followed by a clear 'use when' statement, return value summary, ecosystem caveat, and failure behavior. Every sentence contributes distinct, non-redundant information, and the length is justified given the tool's complexity.

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 fields, per-advisory details, links, and alternative versions returned. It also explains the partial-failure behavior and the NPM-only scope, making the description complete enough for an agent to invoke the tool confidently without needing further context.

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?

Both parameters already have full schema descriptions, so the description adds little new semantic meaning. The 'NPM ecosystem only' note reinforces package scope but is largely redundant with the schema field that already calls it an npm package name. The description does not introduce any syntax or format details beyond the schema, so the baseline 3 for high schema coverage 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. It clearly distinguishes itself by naming the two data sources (deps.dev and bundlephobia) and by explicitly limiting to the NPM ecosystem in v1, thereby differentiating from the alternative 'deps.dev:version' path mentioned for other ecosystems.

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 states exactly when to use the tool: whenever an agent asks 'is X safe / popular / small' or 'what does adding lodash cost me'. It also provides an exclusion/alternative by noting that PyPI/Maven/Cargo/Go packages should fall under deps.dev:version directly, giving the agent clear guidance on 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.