tap_on

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

With no annotations, the description carries full behavioral disclosure. It reveals that WebView taps report COMPLETED without effect, explains the noLaunch param to avoid disturbing modals, and notes required bundleId. While it covers key traits, it could be more explicit about state requirements and return 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 a single, well-structured paragraph. It front-loads the main action and targeting methods, then adds critical warnings. Every sentence serves a purpose with no redundancy, achieving high efficiency.

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 no output schema, the description covers key aspects: action, targeting, required parameters, and a notable false-completion scenario. However, it lacks an explicit statement of return values or error handling, leaving a minor gap.

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 100%, so baseline is 3. The description adds value beyond schema by explaining text matching behavior (anchored regex, fallback to substring), emphasizing bundleId necessity, and clarifying double/long press modes. This extra context raises the score.

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's function: tap, double-tap, or long-press on-screen elements via an ephemeral Maestro flow. It specifies targeting methods (text/regex, accessibility id, coordinates) and distinguishes from siblings by covering multiple tap modes.

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: bundleId is required, and WebView content requires coordinates as text/id selectors fail. However, it does not directly compare to sibling tools like tap_with_fallback or swipe, leaving some usage context implicit.

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