Tap

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

Annotations declare openWorldHint=true (side effects possible) and readOnlyHint=false (can modify state). The description adds the 'escape hatch' metaphor which hints at power/flexibility, but omits specifics about return values, execution context (page vs isolated), error handling, or timeout behavior that would help an agent predict outcomes.

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 sentences, zero waste. Purpose front-loaded in first sentence, usage guidance in second. 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?

Adequate for a single-parameter tool, but given openWorldHint=true (arbitrary side effects possible) and no output schema, the description should mention what the tool returns (evaluation result?) or error behavior. Leaves significant gaps for a tool with such broad capabilities.

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?

With 0% schema description coverage, the description must fully compensate but fails to do so. While 'Evaluate JavaScript' implies the 'expression' parameter contains JS code, the description never explicitly documents the parameter's purpose, expected format, or that it should be a valid JavaScript string.

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 ('Evaluate JavaScript') plus context ('in the browser'). The 'universal escape hatch' phrase effectively distinguishes it from the numerous sibling tap.* tools by positioning it as the fallback when specific tools (tap_click, tap_type, etc.) are insufficient.

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 when-to-use guidance ('use when other tap.* tools can't do what you need'), clearly positioning it relative to siblings. Lacks explicit when-not-to-use exclusions (e.g., prefer specific tools for simple actions), but the escape hatch framing makes this reasonably implicit.

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