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

Goes well beyond the annotations by disclosing that changes are committed to the cluster's GitOps repository and only deployed on the next reconcile (async), the append-on-rerun upgrade behavior, the refusal precondition, and that the action is reversible by deleting the stack. This meaningfully complements readOnlyHint=false / destructiveHint=false.

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 core action and its components before layering on the upgrade, refusal, and reversal conditions. Dense but every clause carries distinct operational meaning; slightly long, but nothing is 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?

With no output schema, the description still conveys that deployment happens on next reconcile, what happens on re-run, when the call is refused, and how to undo it. For a mutation tool of this complexity, an agent has everything needed to invoke it correctly.

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?

Only one parameter (cluster_id) and schema coverage is 100%, so the schema already documents it fully. The description adds no syntax, format, or defaulting detail about cluster_id itself, 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 (Publish) and a concrete resource (the curated security baseline stack), then enumerates its members (trivy-operator for vulnerability/SBOM/compliance plus pod-security policies in audit mode) and the required permission scope. This is distinguishable from siblings like get_cluster_baseline or list_cluster_security_stacks, which read rather than publish.

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 clear conditions: re-running on a cluster with an older baseline appends missing members (the supported upgrade path), and a cluster already running trivy-operator outside the baseline is refused. It stops short of naming an explicit alternative tool or a when-not-to-use-this-instead statement, so it is strong context but not full routing guidance.

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