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

Annotations already establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely valuable semantics beyond that: empty affected_packages is not evidence of no impact, a missing Red Hat VEX during a stale feed is an acquisition gap, rejected records carry rejected:true, and not-found over a stale feed carries absence_caveat. However it omits operational behavior an agent would want, such as latency, rate limits, or freshness-feed behavior, so it is strong on caveats but not on runtime traits.

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 opening clause is well front-loaded and states the payload scope fast. After that it becomes one dense unbroken block mixing caveats, licensing attributions and version cutoffs, with no paragraphing or headings, which makes it harder to scan than its content warrants. Most sentences do carry real information, so this is a density/formatting problem rather than padding.

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?

There is no output schema, so the description must carry the return-value burden, and it does: it explains the affected_packages row shape, the redhat VEX status vocabulary, exploit_signals per-source semantics, and the ATT&CK mapping version and cutoff date. For a read-only lookup with annotations covering safety, nothing material is missing.

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 description coverage is 100%, so cve_id, include_cpe, include_exploits and include_references are already documented. The description implicitly maps the three include_* toggles to the CPE, exploit and reference sections it lists, but adds no format rules or defaults beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb and resource ('Get complete details for a specific CVE') and then enumerates the exact payload domains: CVSS, references, CPE mappings, KEV, EPSS, exploit references, CISA ICS advisories. An agent can immediately tell this is the single-CVE drill-down, distinct from the search/listing siblings.

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?

Gives a concrete usage context — 'use this to enrich an OT/ICS or robot-cell TARA with live advisory context' — which tells the agent the scenario this tool serves. It stops short of naming an alternative (e.g., search_cve for discovery) or stating when not to call it, so it lacks explicit exclusions.

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