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

With readOnlyHint=true already covering safety, the description adds useful behavioral context beyond annotations: the returned summary fields, that not-ready deployments sort first, and that list responses carry total, returned, truncated and scope. It does not cover error behavior or label-selector semantics, but it meaningfully enriches the read-only picture.

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?

Three sentences, each earning its place: the first defines return fields, the second explains ordering, and the third covers list-scoping requirements. The main purpose is front-loaded and there is no filler.

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 five-parameter, read-only Kubernetes listing tool with no output schema, the description does well by naming the summary columns, sort order, and list metadata. It stops short of describing named-read output or label-selector effects, but the schema covers those details, so the remaining gap is minor.

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 the schema already documents all five parameters. The description restates the namespace/all_namespaces list requirement but adds no new meaning for name, cluster_id, or label_selector. Baseline 3 is appropriate 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?

The description gives a specific verb and resource: 'Fetch deployment summary rows', and it names the exact fields returned. The resource 'deployments' clearly distinguishes it from sibling tools such as get_pods, get_daemonsets, and get_statefulsets. An agent can identify what this tool retrieves without opening the schema.

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 states a key usage condition: a list needs namespace or all_namespaces=true, while a named read needs neither. However, it does not say when to choose this tool over alternatives like get_application_deployments, get_stack_deployments, or describe_resource. Usage is implied by the resource name, but alternative routing is absent.

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