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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and non-destructive, so safety is covered. The description does add real conceptual context by defining what a "loop" is and that it signals backtracking/possible confusion, which helps interpret the output; it does not add permission, rate, or pagination behavior beyond that.

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, purpose front-loaded, definitions placed before the ID-sourcing instruction. It is tight overall, though the vague phrase "the documented defaults" gestures at the schema rather than stating the fallback directly.

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 no explanation, and required testId plus the neutral safety profile are handled by structured fields. Still, for a 4-parameter analytical tool with low schema coverage, the description omits the default result count (8, max 20) and gives no cue on how this lens differs from its analytics siblings.

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 only 25% (blockId is the lone documented parameter). The description partially compensates by pointing to list_test_blocks for the targeting IDs and noting that omission falls back to "documented defaults," but it says nothing about limit's range/meaning or what testId/runId require beyond their regex patterns.

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?

It states a specific verb and resource ("List screens participants returned to after leaving") and even defines the term "revisit," so the agent knows exactly what data it gets. It does not distinguish this from close analytical siblings like list_paths, list_dropoff_points, or list_screen_metrics, which is the only thing keeping it from a 5.

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?

"Use IDs from list_test_blocks to target a block/run" gives a concrete routing hint toward a sibling for obtaining valid IDs, and it notes legacy tests are supported. However, there is no guidance on when to choose this tool over the nearby path/dropoff/loop-adjacent analytics tools, so usage is implied rather than delimited.

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