kernel

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

With no annotations, the description carries the behavioral disclosure burdenches and meaningfully warns that restart 'clears ALL definitions and closes subkernels properly'. It also signals that abort() is a lighter-weight alternative for slow evaluations. It could disclose more about subkernels and reap, but the most destructive behavior is exposed.

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 tight sentences: the first establishes the tool's domain and action set, and the second delivers the critical caution about restart and the preferred alternative. No filler or redundant restatement of the schema.

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 output schema may cover return values, but for an admin tool with five distinct actions, only restart is given meaningful semantic detail. 'state', 'subkernels', and especially 'reap' are jargon-heavy and remain unexplained, leaving an agent to guess at their effects.

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 schema provides the enum values but no per-value descriptions, and schema description coverage is 0%. The description repeats the action list and explains restart, which adds some meaning beyond the bare enum, but state, subkernels, and reap are left to inference.

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 identifies the resource as kernel administration and lists the five supported actions, so an agent can see the tool's scope. It does not fully distinguish the kernel 'abort' action from the sibling 'abort' tool, though the preference hint points toward that relationship.

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 selection guidance: 'restart' is a heavy operation that clears all definitions, while abort() is preferred for a merely slow evaluation. It does not provide when-to-use guidance for state, subkernels, or reap, but the action enum and kernel-administration framing carry some of that weight.

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