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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavior beyond annotations: ordering, per-entry contents (old/new branch weights, per-branch success stats, killed branches, reasoning string), and the node-or-workflow scoping. It doesn't mention pagination or result limits, but for this read-only audit listing the disclosure is strong.

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?

Three sentences with no filler: the first states purpose and ordering, the second describes the returned entries, and the third gives invocation requirements and points to the manual sibling. The structure is front-loaded and every sentence earns its place.

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 simple read-only log tool, the description covers what is returned, how results are ordered, what input to provide, and how to trigger a manual optimization via a sibling. The main gap is that the input schema does not actually declare nodeId/workflowId, so the agent must rely on the description to construct arguments, and pagination/limit behavior is unmentioned.

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 zero properties, so the description is the only source of invocation guidance. It names nodeId and workflowId and indicates that either can be provided. This adds real meaning beyond the empty schema. However, the empty schema conflicts with the instruction to provide these identifiers, and their types/format are not specified, which prevents a higher score.

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 ('List'), a concrete resource ('audit trail of split-node auto-optimizations'), and a clear scope ('for a workflow node or a whole workflow'). It also adds ordering ('most recent first'), making it easy to distinguish from the many sibling list/get 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?

The description gives clear context for when this tool is relevant and explicitly names the sibling campaignstack_optimize_split_node as the alternative for triggering an optimization manually. It does not spell out when-not-to-use cases, but the read-only audit purpose and the manual-vs-log distinction are clear.

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