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

Discloses critical runtime behavior beyond annotations: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, sources_failed will include timeouts. Annotations already mark as read-only and idempotent, and description adds complementary detail without contradiction.

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?

Dense and informative; first sentence captures core composite check, then details follow. Slightly long but every sentence adds value. Could be trimmed slightly, but still effective.

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 no output schema, description completely enumerates return fields (summary block, per-advisory detail, links, alternative versions) and partial failure behavior. Covers all essential information for a complex external data aggregation 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 covers both parameters with 100% description coverage. Description adds context that version defaults to latest and that scoped packages are accepted, which is helpful but not essential 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?

Description clearly states the tool is a composite check for evaluating npm packages across deps.dev and bundlephobia. It uses specific verbs ('fan out','returns') and identifies the exact question it answers ('should I add this npm package to my project'). Distinct 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 tells when to use ('when agent asks is X safe/popular/small or what does adding lodash cost') and when not to ('PyPI/Maven/Cargo/Go fall under deps.dev:version directly'). Provides clear context for decision-making.

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