find_text_on_screen

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

With no annotations provided, the description carries the full burden. It mentions it is an 'OCR-search' and returns coordinates but does not disclose that OCR may be slow or error-prone, what happens if text is not found (returns null? throws?), how it determines scope (e.g., auto-detect), or any system prerequisites. It also doesn't indicate whether it performs a single search or a continuous loop. The description is too thin for a tool that could have significant behavioral side effects (e.g., triggering OCR engine).

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?

The description is very short (one sentence) and front-loaded with the key purpose and output. There is no wasted text. However, it is perhaps too short given the need for parameter and behavior information, but conciseness is about efficiency, not completeness. It earns a 4 for being succinct and front-loading the critical info.

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 is moderately complex with 5 parameters and an output schema. Given the context of a screen interaction tool, the description should explain the meaning of 'scope', 'region', 'window', 'monitor', and what the return value looks like (e.g., x, y coordinates or null). It lacks clarity on how to use these parameters effectively. Also, it should note that the tool is often used with 'mouse_click' and 'click_text'. The description is insufficient for effective usage.

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%, meaning the description provides no details about 'target', 'scope', 'region', 'window', 'monitor'. The description says search for text, but 'scope' and 'region' are ambiguous; 'window' and 'monitor' suggest scoping, but no explanation is given. With zero coverage, the description must compensate, but it doesn't. It adds only the trivial 'target' is the text, which is inferable from the schema.

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 ('OCR-search') and a clear resource ('text') and importantly specifies the output ('absolute coords for mouse_click'), which distinguishes it from OCR-recognition tools. It doesn't name any sibling explicitly, but the context (sibling tools like 'click_text', 'wait_text') implies it's the search part of the pipeline. It is clear and actionable.

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 description gives no explicit guidance on when to use this tool versus alternatives. It implies usage by the name and output ('for mouse_click'), but doesn't mention that it should be used before 'click_text' or how it differs from 'wait_text' (which likely searches for text but waits). There is no 'when not to use' or alternative mentions.

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