observe_ui

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

With no annotations, the description must carry the behavioral disclosure burden. It does reveal that the snapshot is compact, token-frugal, current-screen-based, and that actionable elements include refs. However, it does not mention side effects, failure conditions, or whether it relies on the accessibility hierarchy, though 'snapshot' suggests a read-only operation.

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?

One compact sentence that front-loads the key behavior and adds a useful detail about refs. There is no filler or repetition of the tool name.

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 tool has no output schema and no annotations, so the description should explain enough about return values and the optional device_id parameter to allow correct invocation. It leaves device_id undocumented and does not describe what the snapshot contains beyond refs, which is incomplete for a tool in a large sibling family.

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 single parameter device_id has no schema description and the tool description does not mention it at all. Since schema description coverage is 0%, the description was required to compensate and failed to explain what device_id means or how it affects the snapshot.

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 a specific action (Capture) and resource (a compact, token-frugal snapshot of the current screen), and the parenthetical about actionable elements receiving [ref=eN] distinguishes it from siblings like take_screenshot and dump_ui. An agent can identify what this tool does without opening the schema.

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 explicit guidance about when to use observe_ui versus alternatives such as dump_ui, take_screenshot, or find_element. The phrase 'token-frugal' implies a use case, but no when-to-use or when-not-to-use conditions are stated.

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