Look

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

No annotations are provided, so the description carries the full burden. It discloses the output line format (#idx class 'text' id=res @(x,y normalized) [tap]), which is genuinely useful behavioral context, but says nothing about read-only semantics, how 'limit'/'everything' affect results, or what happens with multiple devices. Significant gaps remain for a zero-annotation tool.

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 short and front-loads the purpose, which is good. But the second sentence is an unexplained format legend ('[tap]' is never defined) that reads as cryptic shorthand rather than self-contained guidance.

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 needn't be re-explained, but for a core inspection tool with three fully undocumented parameters and no annotations, the description is far too thin to let an agent invoke it correctly (e.g., when to set 'everything' or how to target a device).

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?

Three parameters (limit, device, everything) with 0% schema description coverage, and the description mentions none of them. It does not explain pagination via limit, device targeting, or what 'everything' expands, so the parameters are entirely undocumented in both schema and description.

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 names the resource ('current app + compact UI node list') and effectively tells the agent this is a text-based UI inspection returning nodes, which distinguishes it from the image-based 'screenshot' sibling. However, it uses no clear verb and the phrasing 'Look' plus the cryptic format legend leaves the actual action somewhat vague.

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?

There is no statement of when to use this tool versus alternatives. The sibling set (tap, tap_node, screenshot, devices) strongly implies this is the node-discovery step preceding tap_node/tap_anchor, but the description never says so, leaving the agent to infer the workflow.

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