Get an A/B test

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real context: required scopes (learning:read, luca:read), full_content data sensitivity, and the default-workspace override behavior. The line 'Does not require idempotency' is about idempotency keys rather than behavior, and sits slightly awkwardly next to idempotentHint=true, though it is not a direct contradiction.

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?

Front-loaded with the purpose and the payload shape, followed by a compact operational block (endpoint, scopes, sensitivity, workspace override). Each line carries information; only the 'small samples swing widely' sentence leans advisory rather than definitional.

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?

With an output schema present, the description need not explain return values, and it covers the operationally important gaps: auth scope, sensitivity tier, and workspace resolution. An agent has everything needed to call it correctly.

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 coverage is 67%: the workspace parameters carry their own descriptions and id has a UUID pattern but no prose. The description adds the piece the schema lacks — that workspaceId/workspaceSlug override a default workspace configured by the environment — which is meaningful semantics beyond the field text.

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 and resource ('Read one A/B test') and immediately scopes the payload ('with its per-variant numbers: how many leads each arm saw, and how each is doing against the success metric'). The word 'one' plus the sibling luca_learning_ab_tests_list makes the single-vs-list distinction obvious without opening any schema.

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?

Usage is only implied: it is a read of an existing test by id, and it warns 'say how many leads each arm has before calling a winner'. That is interpretive guidance for the result, not a when-to-use-this-vs-alternative statement, and no sibling (e.g. the list or panel tool) is named as the alternative.

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