compare_replicas

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It lists the specific dimensions inspected and the conditions it flags, giving an agent a strong sense of what the tool analyzes and surfaces. It does not explicitly state that it is read-only or side-effect-free, but the compare-and-flag framing strongly implies a diagnostic read 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 extremely concise while remaining informative. The front-loaded question captures the primary use case immediately, and the second sentence packs the comparison dimensions and flag categories with no filler.

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 tool with only two parameters, thorough schema coverage, and no output schema, the description gives enough context to know when and how to invoke it. It communicates the comparison dimensions and potential findings. Minor ambiguity remains around terms like 'usage' and 'leaks', but these are acceptable domain terms.

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%: both `service` and `namespace` have clear descriptions in the schema. The tool description adds workload/replica context but does not materially extend the parameter semantics beyond what the schema already provides, so the baseline of 3 is 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?

The description clearly identifies the tool's purpose: determining whether one replica is an outlier by examining per-pod usage, restarts, node, and revision hash, and flagging issues like hot pods, leaks, stuck rollouts, and missing node spread. It is specific enough to be distinguished from general pod-status tools, but it does not explicitly name a sibling tool for differentiation.

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 opening question 'Is one replica the outlier?' implies a clear use case for this tool, and the rest of the description reinforces when it would be helpful. However, it does not explicitly provide when-to-use/when-not-to-use guidance or mention alternative sibling tools such as get_pod_status or diagnose_service.

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