get_changes

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

Annotations already declare readOnlyHint=true and openWorldHint=false; description adds behavioral traits like ranking spec/config changes first, field-level diffs for Deployment env/probes, and structured ConfigMap data. Could mention what is not returned (e.g., non-changes) but overall adds value beyond 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?

Four sentences, front-loaded with use case, then details. No filler, but could be slightly more concise. Well-structured for quick consumption.

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?

Given 5 parameters, no output schema, and behavioral complexity, the description covers purpose, usage, filtering, and return characteristics. Could mention default time window (1h) from the since parameter but schema already does. Reasonably complete.

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 100% with descriptions for all 5 parameters. Description adds usage semantics: 'pair with since to bound the window; filter by...; omit namespace when the relevant change may be outside the app namespace.' This provides context beyond the schema descriptions.

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 clearly states the verb 'returns' and the resource 'recent meaningful changes' with specific ranking (spec/config first). It distinguishes itself from siblings like get_events and get_cluster_audit by noting it's faster than ReplicaSet histories or individual audit/log streams.

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: 'when the symptom is this worked earlier or something broke after a deploy/config change.' Provides alternatives context ('faster than reading ReplicaSet histories') and guidance on filtering parameters (pair with since, omit namespace for cross-namespace changes).

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