get_pod_logs

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

Annotations already declare readOnlyHint=true, which the description matches ('Read...'). It goes beyond the annotations by warning that logs 'may contain sensitive application data' — a genuinely important behavioral disclosure — and by stating the read is a 'bounded tail', so the agent knows it is not streaming or fetching the entire log. No contradictions with 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?

Two short sentences, front-loaded with the verb and resource; both sentences earn their place, including the sensitive-data warning. Slightly under-sized for the parameter complexity, hence not a 5.

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?

The output schema covers return values and annotations cover the safety profile, so the description does not need those. Given 0% schema parameter coverage, however, the description leaves the meaning of previous, container, and tail_lines largely implicit and gives no sibling routing guidance. Adequate minimum, with clear gaps.

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 0%, so the burden falls on the description. It only hints at tail_lines ('bounded tail') and container ('container logs'); it says nothing about how cluster, namespace, name, previous, or container behave (e.g., null container meaning all containers, previous referring to previous pod incarnation). For a 6-param tool this is insufficient compensation.

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 states a specific verb ('Read') + resource ('container logs') + a key qualifier ('bounded tail') that clearly distinguishes it from sibling read tools like describe_pod, get_resource and list_pods. An agent can tell this is log access, not resource inspection or listing.

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?

There is no guidance on when to prefer get_pod_logs over describe_pod, get_resource, or list_resources, and no indication of the crash-debugging use case that the 'previous' flag serves. The description is not misleading, but it leaves all routing decisions to the agent.

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