Get CVE

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety and behavior profile. The description adds the specific fields returned (description, CVSS, affected products, references, linked threats), which is useful context. There are no contradictions, but the description adds only moderate behavioral detail beyond what annotations already provide.

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 efficient sentence that front-loads the purpose ('Look up a CVE by identifier') and then enumerates the return content. No filler or redundancy. It could arguably be slightly more detailed given the sibling landscape, but for what it covers it's lean and well-structured.

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?

The tool is a single-parameter lookup with a near-certain output schema (not shown to the model), fully documented parameters, and comprehensive annotations. The description enumerates the return fields, which is sufficient for a deterministic lookup. Given the low complexity and rich structured metadata, the description is adequately complete — the only gap is distinguishing from the many sibling get_* tools.

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 a single self-explanatory parameter (cve_id with example). The description reinforces the format with the example CVE-2024-3400. Since the schema fully documents the parameter, the baseline of 3 is appropriate — the description adds no new semantics beyond the schema, but none are needed for a single well-documented 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 uses a specific verb ('Look up') and a clear resource (CVE by identifier), and enumerates the fields returned (description, CVSS, affected products, references, linked threats). It's clear but doesn't explicitly distinguish from sibling get_cve_intelligence or search_vulnerabilities, which is a modest gap given how similar get_x tools exist.

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 example identifier and listing of returned fields gives a reasonable sense of when to use it (looking up a specific known CVE), but there's no explicit guidance contrasting with alternatives like search_vulnerabilities (when you don't know the exact ID) or get_cve_intelligence (for deeper intelligence). Usage context is implied by the verb and example, not explicitly stated.

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