get_events

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

Since there are no annotations, the description carries the behavioral burden and meaningfully discloses ordering ('warnings first') and aggregation ('deduplicated with counts'). It does not describe return shape or how deduplication keys are chosen, but the core behavioral contract is visible.

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 information-dense sentences with no filler; the primary behavior is front-loaded and each phrase ('warnings first', 'deduplicated with counts', 'filter by object name prefix') adds value.

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 5-parameter tool with no output schema and no annotations, the description plus schema is adequate for a basic call: namespace, time window, filtering, and warnings-only default are covered. It leaves limit behavior and return format implicit, so an agent has to infer some details.

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 80%, so most parameter meaning is already in the input schema. The description restates the object-prefix filter but adds no semantics for limit, since, namespace, or warnings_only beyond what the schema already provides.

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 identifies the resource as 'Kubernetes events' and adds distinctive behavior ('warnings first, deduplicated with counts'), which separates it from log/error/metric siblings. It lacks an explicit verb beyond the tool name, so it stops short of a fully specified verb+resource definition.

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 only guidance is 'Filter by object name prefix', which addresses how to narrow results rather than when to choose this tool. It never names alternatives such as get_logs or summarize_log_errors, nor does it give exclusions or prerequisites.

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