Collect GPU Trace Summary

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

Annotations provide no safety hints (readOnlyHint=false, destructiveHint=false), so the description carries the burden. It discloses that the tool executes instrumented GPU work and may take minutes, which is meaningful beyond the annotations. It does not mention artifact cleanup, but that is covered in the schema parameter description, so this is adequate.

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 exactly two sentences: the first states the purpose and specific outputs, the second adds the execution time caveat. No redundant explanations, well front-loaded, and every sentence contributes value.

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?

With no output schema, the description lists the returned data fields clearly, giving the agent a good sense of output. It also conveys the runtime cost. It could mention prerequisites like capture existence or architecture override, but the schema and sibling tool context fill most gaps. Overall sufficient for a moderately complex tool.

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?

Schema description coverage is 80%, so the baseline is 3. The description does not add parameter-specific meaning beyond what the schema already documents; it only states the tool operates on a capture and returns summary data. The schema handles parameter details effectively.

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 runs Nsight GPU Trace and returns a specific set of summary metrics (Summary-tab range, Top-Level Throughput, Active Threads Per Warp, SM Warp Occupancy). The verb 'Run' and specific resource distinguish it from sibling tools like get_gpu_trace_report_overview or summarize_gpu_trace_range.

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 the tool is used when a summary of GPU trace metrics is needed and explicitly warns about execution time ('can take several minutes'). However, it does not explicitly state when to use this tool over alternatives like collect_gpu_trace_report or analyze_capture, nor does it provide exclusion criteria.

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