analyze_pytorch

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

The description adds meaningful behavioral context beyond annotations: it explicitly states the tool never triggers extraction and gives a recovery path if data is missing. This is valuable because it prevents the agent from assuming the tool will handle raw traces or extraction. Although annotations already declare readOnlyHint and idempotentHint, the description enriches the behavioral model with the 'never extracts implicitly' caveat and the typed recovery result guidance.

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 highly concise: two sentences with no filler. The first sentence front-loads the primary purpose, and the second delivers an essential usage caveat. Every word earns its place, and the structure is ideal for quick parsing by an AI agent.

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 tool's simplicity (2 parameters) and the presence of an output schema, the description is sufficiently complete. It covers purpose, usage timing, and fallback behavior. The only minor gap is that it doesn't describe what the summary output contains, but that is likely covered by the output schema. The reference to a 'typed recovery result' is slightly opaque but acceptable.

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 coverage is 100% for both parameters, and the schema descriptions are already descriptive: 'Run ID or artifact ID for an imported torch.profiler trace' and 'Maximum operators to return (1-1000).' The description adds no further parameter-specific details beyond restating the input domain. Baseline of 3 is appropriate because the schema carries the semantics.

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's function: 'Summarize normalized Perfetto evidence from a torch.profiler run or artifact.' The verb 'Summarize' and resource 'normalized Perfetto evidence' are specific, and the domain (torch.profiler) distinguishes it from sibling analyze_* tools. The reference to extract_perfetto further clarifies its role as the analysis counterpart.

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 explicit guidance: it is read-only and 'never extracts implicitly.' It also tells the agent what to do when normalized rows are absent: 'follow the typed recovery result and call extract_perfetto for the exact run.' This clearly differentiates when to use this tool versus extract_perfetto, and implies it should be used on existing normalized data rather than raw traces.

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