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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and non-openWorld, so the safety profile is covered. The description adds default sort ordering and legacy-test support, which is useful, but says nothing about pagination, result caps, or how metrics are aggregated, so it slightly exceeds the annotation bar without being rich.

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?

Four compact sentences, front-loaded with what is returned and then the two knobs (sortBy, block/run targeting). No filler, though the closing 'Legacy tests also supported' is terse enough to be slightly ambiguous.

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 the description covers the core selection controls plus ID provenance. The unaddressed limit parameter and the vague 'documented defaults' phrasing keep it from being fully complete.

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 20%, so the description must compensate. It meaningfully explains sortBy, blockId/runId targeting, and the omission default, but never mentions limit or its 1-30 cap, and gives no format guidance for runId vs testId, leaving real gaps.

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?

Specific verb (list) plus resource (screen metrics) and an enumeration of the returned measures (misclick rate, average attempts, total clicks, testers reached), which is more than a restatement of the name. It also references sibling tool list_test_blocks for ID sourcing, giving the agent a routing anchor.

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?

Explains how to use sortBy (default misclickRate descending), how to target a block/run via IDs from list_test_blocks, what happens on omission (documented defaults), and that legacy tests are supported. It stops short of stating when NOT to use this versus related listers like list_insights.

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