ui_find

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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds context about using 'fresh or retained' snapshots, which is a behavioral trait beyond the annotation. However, it does not disclose how criteria in the selector are combined (AND/OR), what happens when no snapshot_id is provided, or what the return value looks like. Thus, some value is added but significant gaps remain.

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?

The description is a single, front-loaded sentence that immediately conveys the primary action and scope. Every word contributes: 'Find matching elements' states the purpose, and 'fresh or retained UI snapshot' distinguishes the two modes. No fluff or repetition.

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?

This tool has a complex, nested selector schema with numerous matchable properties and no output schema. The description provides only the core idea, omitting how to construct a selector, how matches are returned, or how snapshot retention works. It is too sparse for an AI agent to use effectively without further assumptions.

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 schema has 0% description coverage for parameters, so the description must compensate. It only vaguely hints at snapshot_id via 'retained UI snapshot' and at selector via 'matching elements,' but does not explain that selector is a rich search criteria object or how to use its many fields. This is insufficient for a complex two-parameter tool with a recursive selector schema.

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 clearly states the tool's function: 'Find matching elements in a fresh or retained UI snapshot.' This specifies a concrete action (find) on a clear resource (UI elements) and distinguishes it from sibling tools like ui_dump (which captures the hierarchy) and ui_tap (which interacts). The 'fresh or retained' scope adds operational nuance.

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 implies usage—it's for querying elements within a UI snapshot—but does not explicitly state when to prefer this over ui_dump or wait_for_ui. The phrase 'fresh or retained' hints at scenarios with or without an existing snapshot, but no alternatives or exclusions are mentioned. This is implied guidance, not explicit.

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