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

Annotations are sparse (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description carries real behavioral load beyond them: it states the workload drops to zero replicas, the prior replica count is retained, manifests/installation/Ingress host survive, deployment_state becomes 'parked', and a second call is refused as a conflict — which explains why idempotentHint=false. That is exactly the context annotations cannot convey.

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?

Five compact sentences, front-loaded with the core action, then scope semantics, prerequisites, failure mode and negative scope. Each sentence adds a distinct fact — none is filler or a restatement of the tool name.

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?

For a 3-param, non-destructive mutation with annotations, the description covers action, state transition, reversibility, prerequisites and conflict behavior — enough to call it correctly. The only gap is that with no output schema, it doesn't say what the call returns or confirms, though the refusal case is covered.

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 namespace, cluster_id and application_id are already documented in the schema. The description adds workflow-level meaning (use discovery tools to resolve cluster and namespace, and hints that one application can be deployed twice per cluster via namespace identity) but no new parameter semantics. 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?

Specific verb+resource: 'Park one deployment of an Application', immediately defined as scaling the workload to zero replicas while remembering the prior count. It distinguishes itself from siblings by naming wake_application_deployment as the restoring counterpart and by explicitly stating it does not uninstall or delete (unlike remove_application_deployment). An agent can tell exactly what this does versus the delete/scale tools.

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 prerequisites ('Use list_application_installations or get_application_deployments first to find the cluster and namespace') and a refusal condition ('Refused with a conflict when the deployment is already parked'). The counterpart wake_application_deployment is named. What's missing is an explicit when-not pointing at the true removal tool (remove_application_deployment) as the alternative when deletion is intended.

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