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

Annotations already declare readOnlyHint, idempotentHint, etc. The description adds valuable behavioral context: it fans out across deps.dev and bundlephobia, bundlephobia's first measurement can take 5-30s, and partial failures report sources_failed. This goes well beyond 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 informative, front-loading the core purpose. It could be slightly shorter, but each sentence adds value given the tool's complexity. Only minor excess like 'Composite' at start.

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 lacking an output schema, the description comprehensively lists return fields (summary block with specific metrics, per-advisory detail, links, alternative versions). It also covers performance caveats and partial failure behavior, making it nearly complete for an 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 coverage is 100% with clear descriptions for both parameters (package name and optional version). The description adds minor value by restating that the default version is latest and scoped packages are accepted, but doesn't significantly enhance parameter understanding 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 clearly states it performs a composite check for adding an npm package, covering license, advisories, version history, bundle size, dependency count, and ESM/tree-shake support. The verb 'scan' and resource 'dependency' are specific, and it naturally distinguishes itself from siblings like scan_competitor_ai_presence.

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 says 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me".' Also specifies NPM-only scope in v1, and describes graceful degradation with partial failures, which guides when to use alternatives.

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