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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond that: it is a composite fan-out call across two external services, partial failures degrade gracefully via sources_failed, and bundlephobia's first measurement on a new version can take 5-30s. The latency warning and timeout behavior are exactly the kind of operational context an agent needs before invoking.

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?

Four dense sentences, each earning its place: purpose, usage triggers, scope/return shape, and failure/latency behavior. The core purpose is front-loaded. It is slightly run-on in the returns enumeration, but with no output schema available, listing the summary fields is justified rather than wasteful.

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?

For a composite tool with no output schema, the description is remarkably complete: it specifies sources, the summary block's fields, per-advisory detail and links, the NPM-only scope, latency behavior, and partial-failure degradation. Nothing an agent needs to decide whether and how to call it is missing.

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 — both package and version are already documented with examples ('@types/node', '18.3.1'). The description adds ecosystem context (npm-only) and reveals that version interacts with the is_latest output field, but it does not materially deepen parameter-level semantics beyond the schema.

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 states a precise job — 'Composite "should I add this npm package to my project" check in ONE call' — and names the data sources (deps.dev, bundlephobia) and exact data points (license, advisories, bundle size, dependency count, ESM/tree-shake support). It is clearly distinguishable from sibling research tools like validate_claim, compare_entities, and resolve_entity, none of which evaluate npm packages.

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?

Gives explicit trigger phrases: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. It also states a concrete exclusion and alternative: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly'. An agent gets both when-to-use and when-not-to-use with a routed alternative.

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