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

Annotations already include destructiveHint=true. The description adds specific behavioral context: 'Side effect: real mouse click on the remote Windows desktop' and warns about target_id reuse. This goes beyond annotations but still could mention response behavior.

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 with 4 sentences, front-loaded with the core action. Every sentence adds value: purpose, preference, side effect, caution, and alternative usage pattern. No wasted words.

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 annotations and output schema (present), the description covers essential usage notes including side effects and re-usability constraints. It lacks details on return value, but output schema likely handles that. Mostly complete for a click tool.

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 100%, so baseline is 3. The description adds that target_id comes from the latest screen.observe and that button defaults left, but these are already in schema. No additional semantic value beyond 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 clearly states the tool performs left/right/middle-click on a UIA target identified by an id from the latest screen.observe. It specifies the verb, resource, and source, and explicitly distinguishes it from the sibling tool input.click_xy by stating preference.

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 provides explicit guidance on when to use this tool over alternatives: 'Prefer over input.click_xy' and for click→type→keys sequences, use input.send_actions instead. It also advises not to reuse target_id after the screen may have changed, indicating 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.