observe

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

With no annotations, the description carries the behavioral burden. It communicates that this is a read operation and that images are optional, which is useful. However, it does not explain what happens when expected_app or expected_label are provided, what the response structure is, or whether any state is altered.

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 short sentences carry the main purpose and a useful behavioral hint with no wasted words. The core action is front-loaded and the optional-image guidance is placed second, which is an efficient structure.

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 observation tool, the description is minimally viable: it states what is read and warns about image usage. However, there is no output schema and no explanation of the optional expected_app/expected_label parameters, so an agent cannot fully anticipate all behaviors or return values.

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 description coverage is 0%, so the description needed to compensate. It only adds meaning for image ('only when useful'); device, expected_app, and expected_label are left to inference from their names. This is a clear gap for correct invocation.

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 uses a specific verb ('read') and names precise resources ('app, focus, labels, and values'). 'Fresh' clarifies it is about current UI state, which clearly separates it from action-oriented siblings like act and control and list-oriented siblings like devices and apps.

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 gives a clear conditional guideline: 'Request an image only when useful.' It also implies the tool should be used when fresh UI state is needed. It does not explicitly name alternatives or when-not-to-use cases, so it stops short of full routing guidance.

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