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

Annotations already cover the safety profile (readOnlyHint=true) and the description restates 'Read-only' consistently. It goes further by disclosing the scope of returned data (which event categories appear, timestamped), the default look-back (48h) and hard ceiling (14 days), which an agent needs to interpret completeness of results.

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 core purpose, then the event inventory, then usage guidance; every clause carries signal and nothing is padded. Slightly long as a single dense paragraph, but no sentence is wasted.

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, so the description must characterize the return payload, and it does (timestamped state transitions of the listed categories). Combined with the stated window default and max, an agent has everything needed to call and interpret this correctly.

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 kind, name, namespace, cluster_id and window_hours are already documented, including defaults and the 336-hour maximum. The description echoes the default window and max but adds no syntax or selection nuance beyond the schema, making the baseline of 3 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 and resource ('state-transition history of one Kubernetes resource') and enumerates exactly what history contains: creation/deletion, status changes, container restarts, scaling events, spec changes, each timestamped. An agent can distinguish this from describe_resource (current state) and get_events (cluster-wide events) 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 use cases ('since when has this been failing/flapping', when a regression started) and names the tools to correlate against — get_execution_trends and get_events — so the agent knows both when to reach for this tool and what to pair it with.

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