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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds substantial behavioral context beyond these: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, and sources_failed will list timeouts while other data still returns. This describes failure modes and latency, which annotations do not cover.

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 longer than ideal, but it packs in necessary details: the composite nature, what each source provides, return fields, ecosystem scope, and failure behavior. It front-loads the primary purpose in the first sentence and then organizes supporting details. Every sentence contributes, though the density might challenge skimming. Overall, it earns its length for a complex tool.

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?

Despite having no output schema, the description explicitly lists the return fields: summary block keys, per-advisory detail, links, and recent alternative versions. It also covers edge cases like timeouts and graceful degradation. For a composite tool with two external dependencies, this is thoroughly complete and leaves little guesswork for the agent.

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 description coverage is 100%, so the baseline is 3. The description does not add significant semantics beyond the schema: it reiterates that package is an npm package name and version defaults to latest, which the schema already states. The only minor addition is implying both parameters are used in the composite check, but this is not essential. The description carries minimal extra meaning for parameters.

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 starts with a specific verb+resource: 'Composite "should I add this npm package to my project" check in ONE call'. It clearly identifies the tool as a composite check that fans out across deps.dev and bundlephobia, and distinguishes itself by scoping to the NPM ecosystem while noting that other ecosystems belong to deps.dev:version directly. This is unambiguous and differentiates it from sibling 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 explicitly states when to use: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me".' It also provides an alternative path for non-NPM ecosystems, guiding the agent away from this tool for PyPI/Maven/Cargo/Go. This is clear usage guidance with alternatives.

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