voice_tap

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

With no annotations, the description does useful work: it reveals that audio is emitted from PC speakers, that Voice Access performs the action, that a black toast confirms it ("Tapped connections"), and that "tap" should be avoided in favor of "click" because Voice Access can confuse it with app names. However, it never states prerequisites such as Voice Access needing to be enabled, nor what happens on failure or timeout, and settle_seconds goes entirely unexplained.

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 definition is front-loaded with the core mechanism, then structured into an enumerated parameter choice list and a short post-action rule. It is dense but every sentence carries operational value; the layout is easy to scan despite the length.

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 five-parameter, side-effecting tool with no annotations and no output schema, the description covers the selection logic and a verification step well, but omits the settle_seconds parameter, any prerequisite check (voice_access_status exists as a sibling), and the return value. An agent still has open questions before a reliable call.

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 0%, so the description carries the parameter burden — and it does so for four of five parameters, explaining index (from the latest screenshot), label (visible button text), va_number (grey pin numbers when "show numbers" is on), and verb (default click, with a caveat against "tap"). Only settle_seconds is left undocumented.

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 gives a concrete verb and mechanism: PC speakers announce "click <name>" and the phone's Voice Access performs the tap. This clearly separates it from the direct-tap siblings (tap, tap_element), though it never names those siblings explicitly, so the differentiation must be inferred from the "BY VOICE" framing.

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?

It specifies "Give ONE of" index / label / va_number and states when each is preferable — va_number "Best for icons without text and for long or ambiguous names" — plus a follow-up instruction to take a screenshot. It stops short of saying when to prefer voice_tap over tap or tap_element, which is the remaining gap.

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