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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses important behavioral traits: it fans out across two external services, partial failures degrade gracefully, and bundlephobia's first measurement can take 5-30s with sources_failed listing timeouts. It also explains what happens on timeout ('the rest still returns'), providing rich context that annotations alone do not. No contradiction with annotations.

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 every sentence earns its place: purpose, use case, return contents, ecosystem scope, and failure semantics are all covered without redundancy. It is front-loaded with the main composite purpose, and the limitations appear after the core context. No filler or tautological phrases; the length is justified by 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?

Given the composite nature (two external services, partial failures, no output schema), the description fully covers usage, ecosystem constraints, return fields, performance caveats, and failure behavior. It enumerates the summary block fields and mentions per-advisory detail and links. There is no output schema, so the description's rich return-value disclosure is essential and sufficient.

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% for both parameters (package and version), and the schema already describes their types, defaults, and scoped package support. The description adds no new parameter-specific meaning beyond what the schema provides; it only reflects the schema's 'latest published version' default. With high schema coverage, baseline 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 the tool's composite purpose: a one-call check for 'should I add this npm package' combining deps.dev and bundlephobia. It specifies the exact resources and data sources, and distinguishes itself by ecosystem scope (NPM only) and differentiation from the direct deps.dev:version fallback. The phrasing 'Composite ... check in ONE call' is a specific verb+resource+scope that fully clarifies what this tool does.

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 provides explicit usage triggers: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me"'. It also gives clear exclusions by stating 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly', naming the alternative tool. This gives the agent concrete criteria for when to invoke this tool versus alternatives.

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