import_artifact

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

With all annotation hints false, the description carries the behavioral disclosure burden. It usefully discloses auto-detection of Chrome traces with Torch profiler markers and the producer-preservation behavior, but it does not explain side effects such as whether existing artifacts are replaced, whether duplicates are created, or what state changes occur on import. No contradiction with annotations exists.

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 tight sentences: the first states the core action and behavior, the second gives the pipeline context, and the third provides a fallback rule. There is no fluff, no repetition of schema content, and the most actionable guidance is front-loaded.

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?

The schema and output schema cover many details, so the description does not need to re-explain parameters or return values. However, for a generic importer with many specialized import sibling tools, the description does not clarify when import_artifact should be used versus import_static_analysis, import_xctrace, import_kernel_build, or import_nvbench, nor does it explain producer preservation beyond the Torch trace case.

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%, which establishes a strong baseline. The description adds value beyond the schema by pinning kind='execution_trace' and producer='torch.profiler' to the Chrome/Torch trace workflow and by clarifying that detection is automatic with a fallback. It does not discuss parameters like source_root or sensitivity, but the schema already describes those adequately.

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 states a clear action ('Import'), a specific resource ('one project-local artifact'), and a distinct behavioral goal ('preserve producer identity'). It is specific enough to distinguish the tool from the many extract_* siblings, but it does not explicitly differentiate itself from specialized import_* siblings such as import_static_analysis, import_xctrace, import_kernel_build, or import_nvbench.

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 gives concrete usage guidance for Chrome/Torch traces: use kind='execution_trace', then run extract_perfetto before analyze_pytorch, and set producer='torch.profiler' when detection is ambiguous. It does not explain when to prefer import_artifact over the specialized import_* tools, so the guidance is clear but not fully comprehensive.

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