stop_dax_trace

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It reveals detailed computational behavior: total query ms, storage-engine ms from subclass-0 VertiPaq scans, formula-engine ms with a floor at 0 due to parallel SE threads, SE query count, and cache matches. This is exceptional transparency and even explains the reason behind the floor.

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 a single dense sentence that packs multiple metrics and a rationale into one clause. Every word is informative, but the complex structure could be improved by splitting into two sentences for readability. It is not overly long and contains no 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 absence of an output schema, the description thoroughly explains return values and the arithmetic behind them. It does not cover sessionId sourcing or potential error conditions, but overall it provides sufficient contextual detail for the tool's core functionality and output.

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 a single 'sessionId' parameter with no description (0% coverage). The tool description never mentions 'sessionId' explicitly, only referring to 'the session', leaving the parameter's meaning and origin to be inferred. With no schema description, the tool description should have clarified this parameter but does not.

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 specifies the verb 'Stop' and the resource 'session's DAX trace', and goes further to describe the detailed output (structured events and Server Timings metrics). It effectively distinguishes itself from sibling tools such as start_dax_trace and dax_benchmark by focusing on stopping and returning results.

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 implies clear usage context: it stops the session's DAX trace, which presupposes a running trace (likely started with start_dax_trace). It does not explicitly mention alternatives or exclusions, but the context is unambiguous and sufficient for selecting the tool.

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