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

Annotations already declare idempotent, read-only, etc. Description adds crucial behavioral details: partial failures degrade gracefully, bundlephobia delay (5-30s), sources_failed list, and return structure. 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?

Front-loaded with core purpose and key behaviors. Later sentences cover edge cases and return format. Slightly verbose in places (e.g., listing all return fields inline), but every sentence adds value. No wasted words.

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?

No output schema, but description enumerates all return sections (summary, advisories, links, alternative versions). Covers failure modes and ecosystem limitations. For a complex composite tool, this is very complete.

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. Description adds that version defaults to latest and scoped packages are accepted, providing extra context beyond the schema. Could be more explicit about validation rules, but overall good.

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?

Description starts with a clear verb+resource ('composite check') and specifies the scope (npm packages). It distinguishes from siblings by listing exact use cases like 'is X safe / popular / small' and mentions ecosystem limitations. Sibling names like 'scan_competitor_ai_presence' and 'search_within' are clearly different.

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 'Use whenever an agent asks...' with concrete examples. Also clarifies what is not covered ('NPM ecosystem only in v1; PyPI / Maven... fall under deps.dev:version directly') and warns about timeout behavior. No sibling differentiation needed beyond this.

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