click_frame

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

With no annotations, the description carries the burden and does well: it explains the fractional coordinate system, that it works even when the frame is rotated/tilted in 3D, and that Wraith auto-corrects aim for animated frames. It does not mention side effects or failure behavior, but the core interaction model is transparent.

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?

Front-loaded with the main action, followed by precise coordinate semantics, a concrete example, aiming guidance, and the use case. Every sentence adds value and structure is clear with code formatting.

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 the output schema exists and annotations are absent, the description covers the essential behavioral and parameter semantics. The only gap is the undocumented include_snapshot parameter, which is optional but still unexplained.

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%, so the description must explain all four parameters. It thoroughly explains frame (number under 'Frames:') and x/y as fractions of width/height, but omits any mention of the optional include_snapshot parameter.

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 action: click a point inside a frame, with the frame identified by its number. It clearly distinguishes itself from sibling clicks (click, click_at) by targeting frames with no readable elements.

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?

Explicitly says to use it for frames with no readable elements (e.g., Cloudflare Turnstile) and to aim with screenshot(). No explicit exclusions or named alternatives beyond that, but the condition is clear.

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