find_by_image

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

With no annotations, the description fully discloses behavior: takes a fresh screenshot, matches against template_path, returns coordinates. It also mentions the threshold parameter and the return JSON structure. It does not detail failure modes (e.g., no match) but the return JSON includes 'found' boolean, covering that.

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 concise (4 lines) with a clear structure: purpose, behavior, return format. It uses an emoji and bullet points for readability. No redundant sentences. Slight improvement could be to group parameter details more explicitly.

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?

Given moderate complexity, output schema included, and good description of parameters and return values, the description is mostly complete. It explains when to use (DOM not available) but does not contrast with sibling tools like click_at_image or vision_locate, which could help.

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% (schema only has type and title), so the description must compensate. It explains template_path as the path to the template image and threshold with default 0.85, but does not explicitly define threshold as matching sensitivity or specify path formats. This adds some value but leaves gaps.

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 clearly states the verb 'find' and resource 'image on the current page' with method 'OpenCV template matching'. It distinguishes from DOM-based tools by noting use when DOM selectors aren't available, and from sibling tools like click_at_image by focusing on finding coordinates rather than clicking.

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 explicitly states 'Use for finding visual buttons/icons when DOM selectors aren't available.' This provides clear guidance on when to use. However, it does not explicitly mention when not to use or directly reference sibling tools like click_at_image or vision_locate, which are alternatives.

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