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, so the safety profile is well covered. The description adds valuable behavioral context beyond annotations: it mentions explicit source timestamps, coverage, and expiry, and it clarifies that the tool returns cached evidence with a declared maximum age (409 on too-old evidence). It also discloses that some parameters are 'unsupported-capability signals' (history_days, compare_sources) and that desired_fields is a preference only, which is important behavioral transparency. No contradiction with annotations.

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 two sentences with zero waste. The first sentence front-loads the core purpose and the key data domains, and the second sentence immediately clarifies scope exclusions. Every word earns its place, and the structure is ideal for an agent scanning quickly.

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's complexity (8 parameters, 4 enums, output schema present) and the rich annotations, the description is largely complete. It covers the core purpose, the data returned, the source timestamps/coverage/expiry, and the negative scope. The output schema exists, so return values need not be described. The only minor gap is that it does not explicitly mention the caching/409 behavior in the description (though max_age_seconds schema does), and it does not name sibling tools for routing. Still, for an evidence-lookup tool with strong annotations and schema, this is a high level of completeness.

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 88%, so the schema already documents most parameters well. The description adds meaning by clarifying the overall semantics: it frames the tool as returning a 'cached source packet' with timestamps, coverage, and expiry, which helps interpret parameters like max_age, changed_since, and desired_fields. It also explicitly states that desired_fields is a preference and that history_days is not implemented history. This adds value beyond the schema, though the description does not need to repeat every parameter detail given the high schema coverage.

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 states a specific verb ('Use for current evidence on a known CVE ID') and a specific resource (CVE ID), and enumerates the exact data domains returned (NVD status, CISA KEV, FIRST EPSS, advisory links). It also explicitly distinguishes what it is not ('Not asset applicability or validated remediation'), which differentiates it from potential sibling tools like company_snapshot. This is a clear, specific, and well-scoped purpose statement.

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 description clearly indicates when to use the tool: when you need current evidence on a known CVE ID, and it explicitly states what it is not for ('Not asset applicability or validated remediation'). However, it does not explicitly name alternative tools or provide a when-not-to-use condition beyond the negative scope. The sibling tools (company_snapshot, submit_fishnet_feedback) are not referenced, so the guidance is clear but not fully comparative.

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