add_view_switcher

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

With no annotations, the description carries the responsibility of disclosing behavior. It does mention building Display-only bookmarks, buttons, and setting the initial state, which covers the main actions. However, it does not mention potential side effects like bookmark list clutter, name collisions, or what happens if the page or visuals don't exist, leaving gaps for a mutation 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?

The description contains useful information but includes subjective fluff like 'THE premium pattern from pro reports' and 'Ground-truthed from a real report,' which do not aid understanding. The core content is front-loaded, but it is slightly verbose and could be tightened.

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?

The description explains the core functionality and the main parameter well, but for a complex tool with 11 parameters, no annotations, and no output schema, it leaves out important details about behavior with missing visuals, page handling, and potential conflicts. It is adequate but not comprehensive.

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 36%, so the description must compensate. It does provide extra context for the critical 'views' parameter by clarifying that visual names should come from list_visuals/add_* results and that the first view defines the initial state. Other parameters like x, y, gap, and button sizes have defaults in the schema, so the lack of explanation is less critical.

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 that the tool builds a view switcher: a button bar that swaps between views, creating Display-only bookmarks, buttons, and setting the initial state to the first view. This is a specific verb+resource combination that distinguishes it from sibling tools like add_bookmark or add_button, which only handle individual components.

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 implies when to use the tool (when implementing the premium view-switcher pattern) and provides a hint that visual names come from list_visuals or add_* results. However, it does not explicitly contrast it with alternatives like creating bookmarks and buttons separately, nor does it state when not to use it.

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