reset_python

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

With no annotations, the description carries full burden. It explains that running executions are killed, old kernel stops, new kernel created, and outputs remain accessible, but fails to mention that in-memory variables are lost upon restart, which is a critical behavioral trait for a reset operation.

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 concise, with a clear first sentence stating purpose, followed by a structured section on boundaries and returns. No unnecessary information, though it could be slightly more compact.

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?

Covers key behaviors (killing running, preserving outputs, new kernel) and return values, but misses mentioning variable loss and does not explain internal terms like 'loommux'. Given moderate complexity, additional context would improve completeness.

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?

No parameters exist (empty schema), and the description adds value by explaining what the reset entails and the return values (status, PID, error). Baseline for zero parameters is 4, and the description meets that expectation.

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?

Clearly states 'restart IPython kernel' with a specific verb and resource, and distinguishes from siblings by noting preservation of execution history. The description explicitly contrasts with other tools like run_python or interrupt_python.

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 implies use when a kernel reset is needed, and explains the behavior, but lacks explicit guidance on when to use this tool versus alternatives (e.g., interrupt_python) or prerequisites. No 'do not use if' statements are provided.

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