pbi_refresh_manage

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

No annotations provided, so the description carries the full burden. It discloses that cancel is destructive (cancels in-progress Enhanced refresh), and describes behavior differences between Enhanced and standard refreshes. Minor lack of detail on side effects of status/details.

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?

Well-structured with sections (Actions, Args, Returns), bullet points, and clear formatting. Every sentence adds value; no fluff. Efficiently conveys all necessary information.

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 complexity (multiple actions, conditional params, output variations), the description is complete. It explains return types for each action and conditional parameter requirements. Output schema is present but description adds value beyond it.

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?

Input schema has 0% description coverage, but the description fully explains each parameter: workspace_id, dataset_id, action (with values), refresh_id (conditional), top (default 5), format (json/table). Adds meaning beyond schema types/names.

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 it manages refresh lifecycle with three distinct actions (status, details, cancel). It differentiates from siblings like pbi_refresh_dataset (trigger refresh) and pbi_scheduled_refresh_report (scheduling).

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 lists prerequisites (refresh_id for details/cancel) but does not explicitly state when to use this tool vs alternatives (e.g., triggering vs managing refreshes). Some guidance is implicit through action descriptions.

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