diagnose

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

The description discloses all key behavioral traits: it bundles resource details, diagnostic context, current+previous logs, recent warnings, recent changes, startup blockers (for workloads), and GitOps status with parsed issues (for reconcilers). It explicitly states what it does NOT include (Secret content). This exceeds the annotations (readOnlyHint) by providing comprehensive insight into the tool's operation.

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 well-structured, starting with the core use case and then splitting into workload vs. GitOps reconciler behaviors. Every sentence adds value without redundancy. It is appropriately detailed for a complex tool without being verbose.

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 the tool's complexity (6 parameters, no output schema) and the 24 sibling tools, the description leaves no gaps. It fully explains the return content for both resource categories, notes limitations (no Secret content), and provides guidance on alternatives. The absence of an output schema is compensated by thorough description of what is returned.

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?

The input schema has 100% description coverage, so the baseline is 3. The description adds significant context for the 'kind' parameter (listing exact resources and what behavior they trigger) and explains the optional parameters (container, tail_lines, since) beyond the schema. It clarifies defaults and behavior, elevating it above the 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?

The description clearly states the tool's purpose: diagnosing broken workloads or GitOps reconcilers by bundling multiple data sources. It specifies the types of resources (Pod, Deployment, StatefulSet, DaemonSet for workloads; Application, Kustomization, HelmRelease for GitOps) and distinguishes from sibling tools like get_resource or get_pod_logs. The verb 'diagnose' plus detailed scope makes it highly specific.

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 description provides explicit when-to-use scenarios (CrashLoopBackOff, OOMKills, etc.) and when-not-to-use ('If you only need ONE facet... prefer the targeted tool' and 'For other CRDs or non-workload kinds, use get_resource'). It also names alternatives, making the usage boundaries very clear.

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