ui_tree

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

The readOnlyHint annotation already indicates a safe read operation, and the description adds meaningful behavioral context by specifying what the tree exposes. It also signals that ui_find is likely the better default, which is useful beyond the annotation, though it does not mention performance or failure behavior when the app is not available.

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?

Two sentences, both purposeful: the first defines the tool's output and the second gives routing guidance. No filler or redundancy.

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?

The description covers the tool's scope, output contents, and relationship to ui_find, which is most of what an agent needs for a simple read-only tool. However, with no output schema and an undocumented optional 'depth' parameter, the definition is not 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?

The schema describes the 'app' parameter as 'Application name from ui_apps', but the 'depth' parameter has no schema description. The tool description adds no parameter-level guidance, leaving the meaning and effect of 'depth' unclear to an agent.

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 identifies the tool as retrieving an accessibility tree for a single application and lists the key data it contains (roles, names, screen bounds, actionable nodes). It also implicitly distinguishes itself from the sibling ui_find by framing this as the whole-window tree option.

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 explicitly says 'Prefer ui_find unless you genuinely need the shape of the whole window,' which gives the agent a concrete rule for choosing between this tool and a sibling. This is clear when-to-use and when-not-to-use guidance.

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