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

With readOnlyHint already covering safety, the description still adds substantial behavioural context: it never contacts the agent, is sub-50ms, reads a single cluster and refuses to span the organisation, and it defines the staleness model (last_seen_at, staleness_seconds, heartbeat refresh default 480, stale_fallback_required at 300s) so the agent can interpret results correctly. This is far beyond what the annotation conveys.

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-loaded with the crucial cache-vs-live distinction, but delivered as one dense run-on block that interleaves usage guidance, parameter semantics and return shape. It also repeats the schema's own namespace/all_namespaces explanation ('a list that names no namespace reads every namespace ... and says so in a note'), which costs space without adding information.

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?

There is no output schema, yet the description still covers the return contract in detail: one summary row per match with kind-specific status fields (phase/ready/restarts/node/reason for Pods, ready/desired plus first unmet condition for workloads, type/reason/object/message for Events), failed-first ordering, the total/returned/truncated envelope, and where to go for full detail. Nothing needed to call it correctly is missing.

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 coverage is 100%, so the baseline is 3, but the description adds usable meaning on top: it explains that omitting namespace reads every namespace and flags it in a note, how to narrow scope, and what the payload carries (total, returned, truncated, scope, citation marker). It does not add much for field_selector beyond the already detailed schema text, so it stays just above baseline.

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 precise verb+resource+mechanism: a 'Structured SQL-backed lookup against the agent's synced resource index (the k8s_resources cache)'. It immediately differentiates itself from the get_pods/get_deployments/get_services/get_configmaps wrappers and from describe_resource, so an agent can route correctly without opening any 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 explicit when-to-use ('exact lookups, label selectors, and JSONB-path filters', inventory and filtering questions) and when-not ('when you need the live object - verifying a change you just made, or confirming state a write depends on'), naming the alternative tools for each case. Nothing is left to inference.

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