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

Annotations only declare readOnlyHint=true; the description goes beyond that with the non-obvious ordering rule (not-ready sets sort first) and the shape of list results (total, returned, truncated, scope), which tells the agent to expect truncation and scoping metadata. It does not cover permissions or failure modes beyond the schema's scope_required note.

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 dense sentences, front-loaded with the resource and its returned fields, then ordering, then scoping rules. The field enumeration is a little listy but every element is genuinely informative and nothing is padded.

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 usefully carries the return-shape burden (field list, ordering, truncation metadata) plus the list-scoping prerequisite. Only the error/edge behavior is left to the schema, so it is close to complete for a read-only list tool.

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 all four parameters are already documented, including the namespace/all_namespaces exclusivity and the cluster_id discovery hint. The description restates the scoping rule but adds no syntax or format detail the schema lacks; baseline 3 is appropriate.

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 (Fetch) and resource (StatefulSet summary rows) and enumerates exactly what each row contains, which cleanly separates it from the sibling workload readers (get_pods, get_deployments, get_daemonsets, get_cronjobs). An agent knows precisely what it gets back without opening a 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?

Gives a clear selection rule for listing: a list needs namespace or all_namespaces=true, while a named read (name) needs neither. It does not name an alternative tool or explain when to prefer a full describe_resource over this summary view, but the scoping condition is unambiguous.

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