get_kubectl_logs

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

With no annotations, the description carries the full burden, and it does disclose useful behavior: the call runs kubectl remotely via SSH and requires kubectl to be preconfigured for that SSH user. But it is silent on security- and failure-relevant behavior for a 13-parameter remote-execution tool — notably what accept_new_hostkey does, how password vs key_path auth is handled, and what timeout governs (connection vs command).

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?

Content is front-loaded with the operation and mechanism, then narrows to pod/container/previous/since specifics; every sentence adds information. Slight awkwardness in 'Optional since limits them to a time window' and no explicit grouping of the connection vs log-selection parameters.

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?

An output schema exists, so return values need not be described, and the log-selection semantics are reasonably covered. However, for a 13-parameter SSH tool with zero annotation coverage, the description leaves the namespace scoping, authentication parameters, host-key handling, and timeout semantics entirely to the schema, which documents none of them.

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% and the tool has 13 parameters, so the description must compensate — and it only meaningfully explains four of them: lines, container, previous, and since (including accepted time formats and absolute UTC form). Critical parameters such as namespace (whose 'default' value silently narrows results), host, user, key_path, password, timeout, and accept_new_hostkey get no explanation at all.

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?

States a specific verb+resource: retrieve the last `lines` log lines of a SPECIFIC kubernetes pod via `kubectl logs`, executed over SSH on a remote Linux host. That mechanism detail (kubectl-over-SSH) plus the emphasis on a single named pod cleanly separates it from describe/events style siblings and from docker/crictl log tools.

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?

Gives concrete condition-based guidance: previous=True is explicitly recommended for CrashLoopBackOff, and container is called out for multi-container pods. Also states the prerequisite that kubectl must be configured for the SSH user on the remote host. It does not name alternative tools (get_docker_logs, get_crictl_logs, journalctl) or say when not to use this one.

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