Click

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals matching semantics via the selector grammar, which is useful, but says nothing about success/failure behavior, what happens when the selector matches nothing or multiple views, whether the call blocks until the view is ready, or side effects. These gaps are significant for a zero-annotation interaction tool.

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 terse sentences with zero waste. The matching grammar is front-loaded immediately after the core action, so the most decision-relevant information is visible first. Every word 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?

For an interaction tool, the description omits key operational details: what happens on a failed or ambiguous selector match, whether a wait is needed before clicking (relevant given the sibling wait_for), and any timeout or blocking behavior. No output schema exists to compensate, so an agent has limited ability to predict outcomes.

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 only 50% (selector has an example, window has no description), so the description should compensate. It does well for selector by documenting the full grammar '#id' | Role 'Label' | 'Label' | Role, going beyond the schema's single example. However, the window parameter remains undocumented in both the schema and description.

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?

Clear verb+resource: 'Tap a view matched by selector' states precisely what the tool does. The selector grammar line adds specificity. It distinguishes from siblings like screenshot, type, and wait_for by their obvious functions, but does not differentiate from invoke_action, which could overlap in purpose.

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?

No guidance on when to use this tool versus alternatives. There is no mention of prerequisites (e.g., needing wait_for to ensure the view exists before clicking), no exclusions, and no mention of how to choose between click and invoke_action. The agent must infer usage entirely.

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