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

Beyond the annotations (readOnlyHint=true, idempotentHint=true), the description adds operational realism: composite fan-out, bundlephobia's first measurement can take 5-30s, and partial failures degrade gracefully with sources_failed listing timeout details. This level of behavioral disclosure goes far beyond what annotations convey and sets accurate expectations for 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 yet every sentence earns its place: definition, use cases, return fields, ecosystem limitation, and failure behavior. The first sentence is a strong, front-loaded summary, and the rest layers specifics without redundancy. It's structured for both quick scanning and deep retrieval.

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 fully by enumerating the return summary block fields (is_latest, license, bundle_kb_min, etc.), per-advisory detail, links, and alternative versions. It also addresses failure behavior, latency, and scope (NPM only), making it a self-contained guide for an agent to invoke and interpret results correctly.

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%, so the baseline is 3. The description adds no new parameter meaning beyond what the schema already provides (scoped packages accepted, version defaults to latest). The mention of 'NPM ecosystem only' is a scope constraint but not a parameter-level detail, so no upward adjustment is warranted.

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 and vivid framing: 'Composite should I add this npm package to my project check in ONE call.' It then names the exact data sources (deps.dev, bundlephobia) and the summary fields returned, leaving no doubt about the tool's function. This clearly differentiates it from the sibling tools, none of which overlap with npm package health checks.

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 is provided: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me".' It also gives a clear exclusion and alternative: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly.' This is the gold standard for when-to-use guidance.

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