Tap

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

Annotations indicate mutation (readOnlyHint=false) and side effects (openWorldHint=true). Description adds critical behavioral context: navigation results ('Returns the resulting url and title'), error handling mechanism (inspect.toasts), and sequencing requirements. Does not contradict annotations.

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?

Four sentences, each serving distinct purposes: action definition, return values, post-action verification, and prerequisite check. No redundant text; efficiently front-loaded with the core verb.

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?

Despite lacking output schema, description documents return values (URL/title). Covers parameter semantics and workflow integration (toasts, find-prerequisite) sufficiently for a single-parameter interaction tool.

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 has 0% description coverage for the 'target' parameter. Description compensates by specifying it accepts 'visible text or CSS selector', providing essential semantic meaning missing from the structured schema.

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 specific action ('Click'), target resource ('element'), and mechanism ('by visible text or CSS selector'). Clearly distinguishes from sibling tools like tap_find, tap_type, and tap_nav.

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?

Provides explicit prerequisite guidance ('Use tap.find first if unsure') and post-action verification protocol ('check inspect.toasts for feedback'). Names specific sibling tool to use alternatively.

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