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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds two useful pieces beyond that — the return contents (two AUCs plus the difference P value) and the assurance that a real algorithm engine executes it rather than an LLM. It says nothing about assumptions such as paired samples, equal-length arrays, or minimum sample size, which matter for a statistical comparison.

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 short segments with the core purpose front-loaded, no filler, and the return value stated in one clause. The bracketed header largely restates the annotation title, which is minor redundancy rather than waste.

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 low-complexity, deterministic three-parameter test with full schema coverage and no output schema, the description covers purpose, when to invoke, return values, and execution trustworthiness. The remaining gap is that it does not state that the three arrays must be the same length and index-aligned, which an agent could get wrong.

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%, so labels, scores1 and scores2 are already documented in the schema, and the description adds no further syntax, ordering, or length constraints. Baseline 3 applies because the schema carries the parameter burden rather than the prose.

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 names a specific statistical procedure and resource — DeLong's test comparing two ROC AUCs — with a bracketed header that states it up front. An agent can tell this apart from act_roc (single AUC computation) by the words 'two metrics... compare which is better.' It stops short of naming act_roc as the sibling to use for a single AUC, so it is clear but not exhaustively differentiated.

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?

It gives a clear triggering condition: the user already has two AUCs and wants to know which is better and whether the difference is statistically significant. There is no explicit when-not or named alternative (e.g. 'to compute a single AUC use act_roc'), so the routing guidance is implied rather than complete.

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