inspect

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds real behavioral value on top: it discloses the data source (accessibility tree), the returned field set, and that an unfiltered call returns the 'whole tree' while find narrows it. It does not mention truncation or the maxNodes/maxDepth caps.

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, front-loaded with what it lists and where the data comes from, then the usage cue, then the parameter tip. Every sentence earns its place with no filler.

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 4-parameter, annotation-covered reader with no output schema, the description adequately covers purpose, source, and filtering. It omits the practical hazard that results are depth/node-capped, which an agent needs to know before trusting completeness of the listing.

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 50%: 'app' and 'find' are documented in the schema and the description reinforces find's filtering behavior. The two undocumented parameters (maxDepth, maxNodes) are never explained in either place, so the description only partially compensates for the coverage gap.

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+resource: 'List UI elements ... of an app's windows via the accessibility tree', and it names the returned fields (id, role, label, value, frame). It also differentiates itself from visual siblings by calling itself 'the preferred way to find what to click'. Clear, though it never names an alternative tool explicitly.

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 preferred way to find what to click' gives strong, actionable context for when to reach for this tool (element discovery before click_element/drag). No explicit when-not-to-use or named alternative, which keeps it short of a 5.

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