start_dax_trace

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

With no annotations, the description carries the burden of behavioral disclosure. It adds useful context: the trace captures specific events, DAXEvaluationLog is automatically dropped on engines that reject it, and there is a one-trace-per-session limit. However, it does not disclose potential performance impact, required permissions, or what happens if a trace already exists, leaving gaps in full 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 two sentences long, front-loaded with the core action, then the workflow and a key caveat. Every sentence carries useful information with no redundancy. It is well-structured and highly 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?

Given the simple schema (one parameter) and no output schema, the description provides substantial context: the exact events captured, the workflow with stop_dax_trace, the automatic drop behavior, and the one-trace-per-session limit. It does not describe the return value or how stop_dax_trace identifies the trace, but for a start-trace tool this is largely sufficient and leaves only minor gaps.

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 has one required parameter (sessionId) with 0% description coverage. The description only indirectly refers to it via 'the session's engine', implying sessionId identifies the session, but it does not explain how to obtain or format sessionId, nor any constraints. This provides marginal value but insufficient to compensate for the absence of schema descriptions.

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 starts an Analysis Services server trace with a specific verb ('Start'), a resource ('Analysis Services server trace'), and enumerates the exact events captured. It differentiates from siblings by naming the companion stop_dax_trace, and the scope is explicit ('on the session's engine'). This is a specific and unambiguous purpose.

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 provides a clear usage workflow: start the trace, run queries to profile, then stop_dax_trace to collect. It also notes a key constraint ('One trace per session'). However, it does not explicitly mention alternative tools or when not to use this tool, though the companion stop_dax_trace is named enough to establish a paired pattern.

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