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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral context: partial failures degrade gracefully, bundlephobia first measurement can take 5-30s with timeout listed in sources_failed, and full detail of returned data.

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?

Description is a single paragraph that packs significant information, but it is well front-loaded with the composite nature and key use cases. Could be slightly more structured with bullet points for returned data.

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, the description enumerates exactly what is returned (summary block, advisory detail, links, alternative versions) and explains partial failures. This is adequate for a tool combining two external services.

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 descriptions for both parameters. The description adds minor context (scoped packages accepted, version defaults to latest) but no additional semantics beyond 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 combines deps.dev and bundlephobia to answer questions about npm packages. It uses specific verbs ('scan', 'fan out') and resources ('deps.dev', 'bundlephobia'), distinguishing it 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 me'. Also notes limitations: NPM only in v1, with fallback guidance to deps.dev:version for other ecosystems.

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