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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds the context that data is 'cached', implying potential staleness, and that filters are optional. This is meaningful behavioral context beyond the annotations, though it does not describe return format or pagination.

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 a single, concise sentence of 12 words. It is front-loaded with the core verb and resource, and every word adds value. No waste or redundancy.

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 tool is a read-only search with five parameters and no output schema, the description is adequate: it specifies the data source (cached CVE/CNNVD) and the available filter types. It does not mention return format or pagination, but the word 'search' implies a list of matches, and the annotations cover the safety profile. It is not as complete as it could be (no alternative guidance), but it handles the core context.

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?

With 0% schema description coverage, the description compensates by mentioning 'CVE or CNNVD' (database), 'distribution' (distro), and 'severity' filters, mapping to the key parameters. The 'search' action implies the query parameter, and limit is self-explanatory. It adds conceptual meaning beyond the bare schema names, though it does not detail every parameter.

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 verb 'search' and the resource 'cached CVE or CNNVD records', with optional filters. It distinguishes this from sibling tools like get_vulnerability (which retrieves a specific record) and search_packages (which searches packages).

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?

The context of searching cached vulnerability records is clear, and the word 'cached' implies a distinction from live lookups. However, it does not explicitly mention alternatives or when not to use this tool, lacking the 'when/when-not' guidance that would earn a 5.

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