analyze_pytorch

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description adds value by disclosing the 'never extracts implicitly' behavior and the recovery flow when data is missing. This clarifies what the tool will and will not do beyond the structured annotations, though it does not go into deep detail about output behavior.

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 two sentences with no wasted words. The primary action is front-loaded, and the important behavioral constraint and alternative routing occupy the second sentence, keeping the structure tight and scannable.

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 read-only analysis tool with full schema coverage, a rich output schema, and clear annotations, this description is complete. It covers what the tool does, its safe read-only posture, the missing-data fallback, and the exact sibling to invoke in that case. Nothing essential is missing.

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 100%, so the parameters are already fully documented in the input schema. The description adds no additional parameter-level detail beyond naming the torch.profiler source, which matches the schema. Baseline 3 is appropriate because the schema carries the explanatory burden.

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 summarizes normalized Perfetto evidence from a torch.profiler run or artifact, using a specific verb and resource. It also distinguishes itself from extract_perfetto by explicitly noting it 'never extracts implicitly,' which helps an agent separate analysis from extraction.

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 explicit routing guidance: if normalized rows are absent, follow the recovery result and call extract_perfetto for the exact run. This directly tells the agent when to use this tool versus a sibling, which is exactly the kind of exclusionary guidance needed.

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