computer.find_text

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

With no annotations, the description carries the full burden. It discloses the use of OCR + accessibility, fuzzy matching tolerance (case, arrows, small typos), and that matches come with bounding boxes. This gives the agent a solid model of the tool's behavior, though it does not mention failure modes or edge cases.

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 sentences with no redundancy. The core action is front-loaded, followed by the output format and matching tolerance. Every sentence earns its place.

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 description covers the main behavior and output format, but for a tool with no output schema and no annotations, it leaves the meaning of limit and threshold underspecified. An agent could still use sensible defaults, but the missing parameter guidance creates a gap.

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 must compensate. It only indirectly addresses the threshold parameter through the fuzzy matching example, and it does not explain the 'limit' parameter at all. Query is implied as the text to find, but threshold/limit semantics are left to inference.

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 specific verb ('Find'), a clear resource ('text anywhere on screen'), and the method (OCR + accessibility). It also mentions fuzzy matching and bounding boxes, which distinguishes it from sibling tools like find_visual and get_ui_tree without needing to open 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 context is clear: use this tool when you need to locate text on screen and get clickable coordinates. It implies the text-focused alternative to visual/UI-tree tools, though it does not explicitly name alternatives or state when not to use it.

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