Computer Read Screen

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

With no annotations, the description carries the burden and does disclose a key side effect: passing target_title changes OS focus (brings a window to the foreground). It also gives the return shape '(x,y) text' and language coverage (Arabic + English). Missing: behavior when no window matches the title (error vs fallback to current screen) and any rate/latency characteristics.

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?

Three dense sentences with the core action front-loaded and no filler. The 'FIRST' capitalisation and 'atomic focus+read' shorthand are terse but readable; a slightly fuller phrasing of the default case would cost nothing.

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?

Output schema exists, so return value explanation is optional though helpfully given. For a one-parameter tool the definition is nearly complete; the main missing piece is the no-match / no-target_title fallback behavior, which an agent needs to call it safely.

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 0% and the single parameter is undocumented in the schema, so the description must compensate — it defines target_title as a substring match on window title, picks the first match, and acts before the read. Slight gap: the empty/default case (read whatever is currently focused) is only implied.

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?

States a specific verb and resource ('OCR the screen'), which immediately distinguishes it from the sibling computer_screenshot (image capture) and from computer_focus_window (no read). An agent can pick it 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?

The 'atomic focus+read — the read cannot miss the target' clause implicitly steers the agent away from calling computer_focus_window then reading separately, which is a real usage rule. There is no explicit when-not guidance, e.g. what to do if multiple windows match or if no title matches.

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