ui_inspect

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

With no annotations, the description carries the full burden. It signals a read-only operation via 'List', and adds practical behavioral context: the cost relative to DOM dumping and the fact returned targets match how other tools expect elements to be named. It does not go into frame handling or pagination, but those are documented in the schema and this is still enough for safe use.

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 three short sentences with no filler. The core purpose is front-loaded, and each sentence earns its place: what it returns, when to use it, and why it is preferable to the alternative.

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 simple inspection tool with a well-covered schema and no output schema, the description gives enough context to select and invoke it correctly. It states the output concept (targets for interaction) and the usage trigger, though it stops short of describing the exact return structure or how it behaves across frames.

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 100%, so the parameters are already well documented and the description need not repeat them. The prose does add mild value by aligning the listed element families with the kind enum, but it doesn't meaningfully enhance understanding of frame or limit semantics beyond what the schema provides.

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 opens with a specific verb and resource: listing what can be interacted with on the current screen, and enumerates the element families included. By adding the target handle semantics, it clearly differentiates itself from both DOM inspection tools and UI action tools like ui_click or ui_fill.

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?

It explicitly states when to use the tool ('when a selector fails and you need to see what is really there') and contrasts it with a heavier alternative ('Far cheaper than dumping the DOM'). It also explains why the tool's naming style matters for downstream tools, giving an agent clear routing guidance without opening schemas.

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