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

Annotations already declare readOnly, openWorld, and idempotent hints. The description adds that partial failures degrade gracefully, with bundlephobia potentially timing out and sources_failed listing it. This is valuable beyond annotations and discloses behavioral traits.

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 well-structured with a clear front-loaded purpose, uses parentheses for additional details, and every sentence adds value. Slightly verbose but not wasteful. Score 4 for being mostly concise.

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 two parameters, 100% schema coverage, no output schema, and rich annotations, the description covers behavior, partial failures, result structure (summary block, advisories, links, alternative versions), and ecosystem limitations. Complete for a read-only tool.

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%, with clear descriptions for both parameters (package name and version). The description reiterates that version defaults to latest, but adds no extra semantics beyond the schema. Baseline score of 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 is a composite check for npm packages, covering license, advisories, version history, and bundle size. It specifies the verb 'scan' and the resource 'dependency', and differentiates from siblings by noting its composite nature and ecosystem limitation.

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?

Explicitly states when to use: for questions about safety, popularity, or cost of adding a package. Also provides when not to use: other ecosystems (PyPI, Maven, etc.) should use a different tool. This gives clear context and alternatives.

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