Collect queryable GPU Trace report

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

The description discloses that collection 'executes instrumented GPU work' and 'can take several minutes', which is valuable context beyond the annotations' generic all-false flags. It also mentions auto-exporting tables in a report session, implying persistence. It doesn't detail cleanup or failure behavior, but the schema parameter descriptions cover some of that, and the time/execution caveat is an honest behavioral disclosure.

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 three concise sentences: the first states the main action and return value, the second explains downstream usage, and the third warns about runtime. Every sentence earns its place, with no filler or redundancy. The structure is front-loaded with the most important 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?

For a tool with 8 parameters, 2 enums, no output schema, and a complex collection workflow, the description covers the essential workflow (collect → report_id → query with other tools) and the key runtime caveat. It doesn't explain error conditions or prerequisites, but those are partially covered by schema parameter descriptions. Overall, the context is sufficient for an agent to understand when and how to invoke the 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 88%, so the parameters are well-documented in the schema. The description itself adds no parameter-level detail, focusing instead on the tool's purpose and workflow. Since the schema already explains each parameter, the baseline of 3 applies and no extra semantic value is provided by the description.

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 'Run a feature-rich Nsight GPU Trace replay' and 'return a report_id', distinguishing it from sibling query tools like list_gpu_trace_reports and get_gpu_trace_report_overview. The verb 'collect' is reinforced by 'retain its report and auto-export tables', leaving no ambiguity about its role as the collection step.

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 explicitly directs users to 'Query that id with the metric, range, trace-information, and shader-occupancy tools', establishing this as the collection step before analysis. It also cautions that it 'can take several minutes', implying it is not for quick operations. However, it does not name alternative collection tools or mention when not to use it, leaving some room for improvement.

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