Click Screen

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

With annotations present (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description adds value beyond them: the server-side validation that display/geometry haven't changed before tapping, and the rejection of ambiguous targets. It does not contradict the annotations — 'click' is consistent with a non-read-only, non-destructive action in an open world.

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?

Three sentences with zero filler: the first front-loads the core action and all targeting modes, the second gives the preference rule, and the third handles the screenshot edge case. For a 7-parameter tool with nested objects and coordinate spaces, this is tightly packed and well ordered — every sentence earns its place.

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 tool's complexity (7 params, nested target object, three targeting modes, coordinate-space handling) and no output schema, the description covers the essential calling concerns: how targets are specified, precedence, ambiguity rejection, and the screenshot/snapshot coupling. The only gap is the unspecified return value, but for a tap action that is typically just success/failure and is a minor omission.

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 the schema already documents all 7 parameters including ref precedence and coordinateSpace semantics. The description adds marginal clarification (rejection of ambiguous target matches, screenshot geometry validation) that largely overlaps with schema text. Baseline 3 is appropriate since the schema carries the load and the description adds only minor complementary nuance.

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 ('Click') and enumerates three distinct targets: raw x,y coordinates, an element ref ('@e5'), or a unique target object. This clearly differentiates it from siblings like mobile_double_tap_on_screen, mobile_long_press_on_screen_at_coordinates, and mobile_press_button, whose verbs/scopes differ. An agent can tell exactly what this tool does and what it does not do.

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?

Gives an explicit internal selection rule: 'Prefer ref or a unique target when the element is listed', plus a hard constraint ('Ambiguous targets are rejected') and the snapshotId requirement for screenshot coordinates. This is strong context for choosing among the tool's own targeting modes, though it never references sibling tools by name or an explicit when-not-to-use condition against them.

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