powerbi_health

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the concrete surfaces inspected (engine availability, store counts, audit log count) and the remediation hints returned, which tells the agent this is a read-only diagnostic operation. It does not explicitly state permissions, side effects, or rate limits, but the diagnostic scope is well described.

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 front-loaded with the core purpose, then uses a clean bullet list to enumerate the diagnostic surfaces. Every sentence adds useful context without waste, and the intended usage note at the end is concise.

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?

An output schema exists, so the description need not fully document return values, though it helpfully summarizes them. The main gap is the undocumented parameter, and with no annotations there is no explicit safety or precondition coverage. It is adequate for understanding the tool's purpose but leaves the single input parameter unexplained.

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 sole parameter, include_engine_details, has 0% schema description coverage, so the description must compensate. While it mentions engine availability and per-engine remediation hints, it never explains what the boolean controls, what the default behavior is, or how toggling it changes the response.

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 states a specific verb and resource: 'Return a diagnostic snapshot of the orchestrator.' It clearly frames the tool as a diagnostic/health check, which distinguishes it from sibling workflow tools like plan_change, apply_plan, and deploy_to_workspace.

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 explains the intended usage context: the LLM should surface missing dependencies and installation hints instead of letting the user hit a workflow brick wall. It does not explicitly name when not to use it or compare against sibling alternatives, but the diagnostic framing makes the appropriate context clear.

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