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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the risk profile is known. The description still adds value by naming the 'native' input path and giving concrete consequence examples (purchases, deletion), but it says nothing about backend/consent behavior, failure modes, or whether the pointer is moved to the coordinate as part of the click.

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?

Two sentences, front-loaded with the action, followed by the safety precondition. Every clause carries actionable information with no filler.

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?

With rich annotations, full schema coverage, and an output schema, the description only needs to convey purpose, precondition, and risk, and it does all three. The gap around pointer-move behavior is minor given the sibling pointer_move tool exists and the schema is self-documenting.

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%, including detailed enum semantics for 'button' and 'backend', so the schema carries the parameter burden. The description only reinforces that coordinates are a 'verified desktop coordinate', adding no format or validation detail beyond what the schema already states, making the baseline 3 appropriate.

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 verb and resource ('send one native mouse click') plus the constraint that the coordinate must be verified. The word 'native' hints at OS-level input versus DOM/synthetic clicks, but the description never names or distinguishes sibling tools like pointer_right_click, pointer_double_click, or computer_click, even though the button enum overlaps with pointer_right_click.

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?

'Check the current screenshot or element bounds first' gives a concrete precondition for use, and the warning about purchases/deletion signals the risk context. However, it offers no exclusions or routing guidance, notably omitting when to prefer pointer_double_click, pointer_right_click, or ui_click over this generic click.

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