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

Annotations already declare readOnlyHint=true, so safety is covered, but the description adds genuine behavioral context beyond them: it reads live from policy reports and, importantly, discloses error behavior ('a cluster that is offline or has no agent answers a refusal naming the cause'). It does not cover pagination or rate limits, keeping it just below the top.

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-loads the subject and packs useful detail (return shape, read-only, failure behavior, follow-up tool) into a few sentences with little waste. It is on the dense side, but nearly every clause earns its place.

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, the description compensates by enumerating what the response contains (per-policy failures, severity totals, audit/enforce mode) and how failures surface. For a single-parameter read tool the definition is essentially complete, with only minor gaps like pagination behavior.

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% and the single cluster_id parameter is already fully documented ('Cluster id (UUID). Optional when the conversation is bound to a cluster'). The description adds no parameter meaning beyond the schema, so the baseline of 3 applies.

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+resource (pod-security policy violations on one cluster) and goes further by describing the exact content returned: per-policy failing resources with namespace/message, severity totals, and audit vs enforce mode. The source ('Kyverno / Pod Security policy reports') and live-read framing make it clearly distinguishable from broader siblings like get_cluster_pod_security.

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?

Provides real usage context: it is read-only, names the failure case (offline / no-agent cluster returns a refusal), and explicitly pairs with set_cluster_security_policy_mode once violations are clean. It stops short of naming exclusions or a competing read tool to use instead, so it is clear context without full when/when-not coverage.

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