Stop a running cloud agent by interrupting its current execution and return whether an active run existed. Use agent_id to target the run and optionally include a reason.
Interrupt the agent's current run. Returns had_active_run.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | user | |
| agent_id | Yes | ||
| session_id | No | Chat session id; default empty MAIN transcript |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the return value (had_active_run) but says nothing about whether the interrupt is graceful or abrupt, what happens to pending widgets/drafts, required permissions, or whether it's reversible. For a mutation-style control tool with zero annotation coverage this is thin.
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 telegraphic sentences that front-load the action and include the return signal with zero filler. Appropriately sized for a single-action tool.
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?
A 3-parameter mutation tool with no annotations, no output schema, and only one undocumented-params return hint. Missing behavioral detail and parameter semantics that an agent needs to call it correctly, even given the simple surface.
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 coverage is only 33%: session_id is documented but agent_id and reason are not, and the description adds nothing about any of them. It does not explain the default 'user' value for reason or how target scope works. With low coverage and no compensating text, the gap is unaddressed.
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?
Specific verb (interrupt) plus resource (the agent's current run), which is distinct from siblings like grokbot_send or grokbot_wait. It also states the return signal (had_active_run), so the agent knows what to expect. It stops short of explicitly differentiating from other lifecycle tools such as grokbot_end_handoff.
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?
No guidance on when to interrupt versus alternatives (end_handoff, wait, resolve_widget) or when not to. No prerequisites or context about what state the agent must be in. The agent must infer all routing from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.