colab_restart_runtime

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It explicitly states that restarting clears all variables/state, which is the most important behavioral consequence. It could additionally mention that running executions may be terminated or that the runtime becomes temporarily unavailable, but the core destructive effect is 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?

The entire description is one focused sentence, front-loading the action ('Restart') and including the critical side effect in parentheses. There is no filler, redundancy, or repetition of the tool name.

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 simple tool with one parameter and no output schema, the description gives the essential purpose and side effect, which is a minimally viable level. However, the lack of parameter guidance and the absence of any statement about preconditions (e.g., session must exist) or what happens to running jobs leaves meaningful gaps for an agent deciding how to call it correctly.

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 has one parameter, session_id, with no description, and schema description coverage is 0%. The description says 'a runtime session' but never explicitly links it to the session_id parameter, its format, or whether it is required or optional. Given zero schema coverage, the description should have made it clear that session_id identifies the session to restart.

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 ('Restart'), names the exact resource ('runtime session's kernel'), and includes the key side effect ('clears all variables/state'). This clearly distinguishes it from sibling tools like colab_stop_execution or colab_cancel_job, which halt work but do not reset the kernel state.

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?

There is no guidance about when to choose this tool over alternatives. It does not state that restart is appropriate when a runtime is unresponsive or when a fresh state is needed, nor does it explicitly say not to use it when merely stopping execution would suffice. The intended use case is only implied by the name and description.

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