add_dashboard_set_action

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

With no annotations, the description carries the full behavioral burden. It usefully describes the runtime effect (the set fills with marks under the pointer and clears on leave), which is genuine behavioral context beyond a restatement. But it omits whether this mutates the workbook, required permissions, whether the target_set must already exist, and side effects on existing actions.

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 short sentences, front-loaded with the action being added and followed by the effect. No filler, though the parenthetical and second sentence could be tightened slightly.

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?

This is a mutation tool with 8 parameters, zero schema coverage, and no annotations, so the description is the only guidance. An output schema exists so return values need not be explained, but the description never states prerequisites, permission requirements, or mutation side effects, leaving significant gaps for an agent to call it correctly.

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 description coverage is 0% across 8 parameters, so the description must compensate and only partially does: 'clears when it leaves' loosely maps to clear_option, 'hover' maps to event_type, and 'set' hints at target_set. The remaining parameters (caption, source_sheet, single_select, selection_mode) receive no semantic help whatsoever.

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 a specific verb and resource ('Add a Set Action') and clarifies the underlying object with the parenthetical '(edit-group-action)', which is helpful for matching Tableau's UI concept. It is distinguishable from sibling actions like add_dashboard_toggle_button or initialize_dashboard_filter_action by naming the specific action type, though it never explicitly contrasts them.

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 second sentence implies the use case ('enabling hover-driven labels and calculations') and the default event_type of on-hover, so an agent can infer when this action is appropriate. However, it gives no explicit when-to-use versus add_dashboard_action or other action siblings, and no prerequisites.

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