extract_nsight_compute

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

All annotations are false, so the description must carry the full burden of disclosing behavioral traits. It mentions the underlying interface but does not disclose whether this is a read-only operation, any side effects, permission requirements, or error conditions. The term 'Extract' implies reading data, but the readOnlyHint is false, leaving ambiguity about side effects or whether it modifies run state.

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, direct sentence with no fluff. It front-loads the action and specifies a key contextual detail ('through NVIDIA's installed ncu_report interface'). It could be slightly more informative, but it is appropriately 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?

Despite the presence of an output schema, the description leaves significant gaps: it does not explain what 'bounded metrics' are, how run_id is used, when the tool should be invoked, or how it relates to other extraction tools. For a one-parameter tool, the lack of parameter and usage context makes the description incomplete.

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 0% description coverage for the single required parameter run_id. The description does not mention run_id or explain how it relates to the extraction. Since the description provides no information about the parameter, it fails to compensate for the schema's lack of documentation.

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 uses the specific verb 'Extract' and identifies both the resource ('bounded metrics') and the mechanism ('NVIDIA's installed ncu_report interface'). The mention of 'ncu_report' distinguishes it from sibling tools like extract_nsight_systems and extract_perfetto. However, 'bounded metrics' is somewhat vague and could be more precise about what kind of metrics are extracted.

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 no guidance on when to use this tool versus alternatives such as extract_nsight_systems or extract_inference_trace. It does not state any conditions, exclusions, or contexts where this tool should be preferred.

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