tap

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

No annotations are provided, so the description carries the full burden. It explicitly states the default side-effect of capturing a screen_snapshot and how to suppress it. This is a key behavioral trait that an agent needs to know. However, it doesn't mention other potential side effects or error conditions, so a 4 is given.

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 extremely concise, consisting of two clear sentences. The first states the core action and input methods, the second provides important usage guidance. No redundant information is present.

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?

For a simple tap action, the description covers the essential aspects: input methods, resnapshot behavior, and results. It lacks information about handling conflicting inputs (e.g., both ref and x,y) or error cases, but the tool is straightforward and the context is well-covered.

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 50% (only ref and resnapshot have descriptions). The description adds meaning by explaining that tap uses either ref or x,y, and clarifies resnapshot's purpose. However, x and y parameters remain without additional explanation beyond the schema type. Baseline 3 is appropriate as the description partially compensates.

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 a tap using a reference (ref) or coordinates (x,y). It also explains the resnapshot behavior. While it distinguishes from sibling tools implicitly by name, it does not explicitly differentiate from similar gestures like double_tap or swipe, so a 4 is appropriate.

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 guidance on when to set resnapshot=false ('only when chaining many acts then one snapshot'), but does not offer broader usage recommendations or when to prefer this tool over alternatives like click or double_tap. The guidance is moderate but incomplete.

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