manage_workload

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

Annotations include destructiveHint=true, so the description adds action-specific behaviors: restart triggers a rolling restart, scale changes replica count, and rollback reverts to a previous revision. It also ties parameters to actions, but does not detail side effects like pod termination or revision history limits.

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?

Two sentences: first states the main purpose, second enumerates actions and provides a discovery hint. Every sentence adds value with no redundancy.

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?

The description covers all supported operations, parameter requirements, target kinds, and the discovery step. The destructive nature is already provided by annotations. For a mutation tool with no output schema, this is adequate.

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?

The schema covers all parameters (100% coverage), but the description explicitly states that 'replicas' is required for scale and 'revision' for rollback, adding conditional requirement semantics not fully captured in the schema.

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 clearly specifies that the tool performs operations on Kubernetes workloads and enumerates the three supported actions (restart, scale, rollback), distinguishing it from sibling tools like manage_cronjob or manage_node.

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?

It explicitly advises using list_resources or get_dashboard first to identify the target, providing a clear prerequisite. However, it does not contrast with alternative mutation tools like apply_resource or patch_resource, so no exclusions are mentioned.

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