screen

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

No annotations are supplied, so the description must carry the full disclosure burden. It does name the two things returned (tree text plus package name), which implies a non-mutating read, but it says nothing about output size, verbosity, whether the tree can be truncated, or whether any permission is needed. For a zero-parameter observation tool this is adequate but thin.

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?

It is a single compact sentence that front-loads the two returned artifacts, with no filler or repetition. The parenthetical framing is short and reinforces purpose rather than padding the text.

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?

There is no output schema and no annotations, so the description is the only place return-value detail could live. It identifies the two return components but not their shape or size, which leaves an agent guessing about how much text to expect. For a simple zero-argument read tool, this is the minimum viable level of completeness.

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 tool takes zero parameters and the schema declares an empty property set, so there is no parameter meaning to add. The description correctly implies the call needs no arguments, and the baseline for a parameterless tool applies.

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 states a concrete verb and two concrete resources: the current screen's accessibility tree text and the foreground app package name. That is far more specific than the tool name 'screen' alone. It does not, however, distinguish this tool from siblings such as ACTION_READ_SCREEN, ACTION_FOREGROUND_APP, mini_screen_status or debug_screen, which appear to overlap.

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 parenthetical '(AI's eyes)' hints that this is the way an agent perceives the screen, but there is no explicit when-to-use rule and no when-not-to-use rule. Nothing tells the agent whether to prefer this over ACTION_READ_SCREEN, ACTION_SCREENSHOT or ACTION_FOREGROUND_APP, even though those siblings clearly compete for the same job.

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