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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with that safe, corpus-local read. It goes beyond the annotations by disclosing the output shape (per-assertion supported/refuted/unverifiable verdicts with cited evidence) and the fact that free-text 'claim' returns summary/CWE evidence for the caller to judge. No permissions, rate limits, or pagination details, but none are needed for a stateless read.

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?

Front-loaded with the purpose and the four verification axes, then usage, then a compact Args block and an example — a sensible order with little waste. The 'catch hallucinations before they ship' clause is mild marketing, and the Args list partially restates schema titles, but the net density is high.

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?

With no output schema and 0% schema coverage, the description must cover both invocation and return; it does, describing the verdict vocabulary and the evidence payload. An agent has everything needed to call it correctly and interpret the result.

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 0%, so the description carries the full burden and does so: it marks cve_id as the id being claimed about, flags product/version/severity/exploited as optional with their semantics ('checks the affected-version claim in range', severity accepts a number or label), and explains claim as free-text evidence mode rather than a verdict. The example call demonstrates correct argument usage directly.

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 ('Fact-check a claim about a CVE against the corpus') and enumerates exactly what is verified: existence, affected product/version, severity, KEV exploitation. This clearly separates it from siblings like search_vulns and enrich_cve, which retrieve rather than adjudicate a claim.

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 an explicit trigger ('check what another agent (or a draft report) asserted') plus a worked example mapping a natural-language claim to an invocation, which is unusually actionable. It stops short of naming alternatives or when-not to use it (e.g., versus search_vulns for open retrieval), so it is clear context without exclusions.

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