get_events

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

Annotations already indicate read-only behavior. The description adds that events are deduplicated, sorted by recency, and include reason, message, and count. This provides useful behavioral context beyond the schema and annotations.

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?

The description is two sentences long, front-loads the purpose and usage scenarios, and efficiently covers what the tool returns and when to use alternatives. No superfluous text.

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 simple event-listing tool, the description covers the key aspects: what it returns (deduplicated events with reason, message, count), when to use it, and how it differs from 'issues'. It lacks an explicit time range for 'recent', but the limit parameter addresses pagination. Overall sufficient.

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% with clear descriptions for all parameters. The description does not add new semantic details about parameters but does provide usage context (e.g., 'after an overview points at a namespace'). This is adequate but not exceptional.

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 tool's purpose is clearly stated: to retrieve recent Kubernetes Warning events for troubleshooting specific symptoms. It distinguishes itself from the sibling tool 'issues' by noting that 'issues' provides a ranked list of problems, whereas this tool returns raw events.

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?

Explicitly states when to use this tool: after an overview points at a namespace/resource or when symptoms like scheduling errors occur. Also advises to use 'issues' first for a ranked issue list, providing clear differentiation.

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