abort

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

With no annotations, the description takes on full behavioral disclosure. It clearly states the key effect—interrupting the running evaluation—and the crucial consequence that the kernel survives with all state intact. It does not cover what happens to the interrupted evaluation or whether abort is reversible, but the most important behavioral traits are disclosed.

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?

Two sentences, each earning its place: the first states the action and its immediate outcome, the second says when to use it and contrasts with the destructive alternative. Information is front-loaded and nothing is redundant.

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 parameterless tool with an output schema and a clear sibling (kernel), the description covers all an agent needs to call it correctly: the action, the effect on kernel state, and when to prefer it over a destructive alternative.

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 tool has zero parameters)Skip; no parameter semantics are needed because the input schema is empty and schema description coverage is 100%. The description adds no parameter information, but this is not a gap for a parameterless tool.

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 a specific verb ('Interrupt') and a clear resource ('the evaluation the kernel is running right now'), precisely identifying what the tool does. It also contrasts itself with kernel(action='restart'), making its role unambiguous among siblings.

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 explicitly tells the agent when to use this tool: for a runaway computation, instead of kernel(action='restart'). It also explains why this choice is better, because restart destroys every definition while abort preserves state.

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