add_narrative_measure

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

With no annotations, the description carries the burden. It explains the measure's logic and live-update behavior, but doesn't address whether it overwrites an existing measure with the same name, required permissions, or other side effects. The 'create' verb makes the mutating nature clear, but more detail would improve transparency.

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 and front-loaded, with the verb and resource in the first phrase. Each sentence provides distinct value: what it creates, how it works, and where to use it. No redundant filler.

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 moderate complexity with 9 parameters and no output schema, the description covers the key functional behavior and usage context. It doesn't mention return values or prerequisites like existing measures, but the schema descriptions and the examples for each measure parameter fill in much of the gap.

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 covers 89% of parameters individually, so baseline is 3. The description adds significant context by explaining that the top-N members are based on contribution to the change (current - prior), which clarifies the roles of currentMeasure, priorMeasure, dimColumn, and topN.

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's function: 'create a dynamic DAX text measure' that names top-N contributors and states overall growth. It distinguishes this from the native smart-narrative visual and from generic add_measure by the auto-narrative behavior.

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?

It implies when to use (for insight text in a card, as an alternative to the native visual) and mentions the live-update behavior with slicers. It doesn't explicitly list exclusions, but the context is clear enough for an agent to select it appropriately.

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