tap_runtime

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

The description adds behavioral context beyond annotations: it explains that chrome provides login sessions and is for write operations, while headless is fast and without login. Annotations indicate idempotentHint=true, which aligns with switching behavior. The description does not contradict annotations and provides useful real-world context, though it could mention if switching resets any state.

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 concise with three sentences, each serving a clear purpose. The first sentence states the main action, the second details when to use each option, and the third clarifies a related but distinct concept. No redundant or vague statements.

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?

Given the tool's simplicity (single parameter, enum, no output schema), the description covers all necessary aspects: purpose, usage guidelines, parameter semantics, and behavioral context. It is complete for an agent to correctly select and invoke this 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?

The schema already describes the parameter with enum values and descriptions. The tool description adds value by stating the default is headless and giving usage advice ('Use chrome when...', 'Use headless to switch back'). This provides practical guidance beyond the schema's literal descriptions.

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 switches browser runtime mid-session, explains the two runtime options (chrome and headless) with their characteristics, and distinguishes itself from sibling tools by clarifying it is unrelated to `tap mcp connect`. The verb 'switch' and resource 'browser runtime' are specific and unambiguous.

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 explicitly tells when to use chrome (need real browser with login sessions, write operations) and headless (fast, no login), and also states the default is headless. It effectively guides the agent on when to use this tool and when not, providing clear context for each option.

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