pbi_create_html_visual

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

Annotations are present (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds behavioral context beyond them: it states that the custom visual is registered in the report if not already present, and clarifies that the HTML is built in DAX (typically with VARs and CONCATENATEX). This is useful side-effect disclosure, though it doesn't cover all failure modes or behavior on existing visuals.

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: two short paragraphs, with the primary purpose front-loaded. The parameter detail is inline and could be better formatted as a list, but it's efficient and free of fluff.

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 complexity (5 params, nested position object, output schema present), the description provides key workflow context: the measure is pre-created via pbi_create_measure, the visual registers itself, and the HTML is constructed in DAX. It does not explain page/position details, but for a Power BI-focused audience these are familiar. The output schema likely covers return values, so the description needn't.

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 input schema has 5 parameters with 0% schema description coverage, so the description must compensate. It only explains html_measure, giving an example, but leaves page, position, title, and request_id undocumented. This is insufficient for a tool where the user must supply page and position correctly.

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 opens with a specific verb and resource: 'Crea un visual "HTML Content"' (creates an HTML Content visual) and explains its function: renders HTML/SVG from a measure. This clearly distinguishes it from generic siblings like pbi_create_visual or pbi_add_custom_visual by naming the exact visual type.

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 explicitly instructs that the measure must be created separately with pbi_create_measure, providing a direct cross-reference to a sibling tool. It also gives an example measure name ('[HTML Panel EVM]'). This gives clear context for when this tool is appropriate, though it does not state explicit 'when-not-to-use' scenarios.

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