Pause an active run and route it to a human intervention lane, supplying a prompt and actor context to request decisions and coordinate approvals.
Move an active run into a local awaiting-human lane.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| run_id | Yes | ||
| actor_id | Yes | ||
| actor_role | Yes | ||
| decision_packet | No | ||
| intervention_kind | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.2.6Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the high-level action; it does not mention side effects, reversibility, whether the human lane persists, what happens to the run after intervention, or any authorization requirements. This is insufficient for a mutation-style tool.
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 a single, tightly worded sentence with no filler. It front-loads the action and destination. However, its brevity comes at the cost of omitting essential behavioral and parameter context.
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?
Given the tool has six parameters, five required, no parameter descriptions, and no annotations, a one-sentence description is far from complete. The presence of an output schema reduces the need to document return values, but does not compensate for absent parameter semantics, usage guidance, and side-effect disclosure.
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 description coverage is 0%, and the description adds no meaning to any of the six parameters. Terms like intervention_kind, decision_packet, and actor_role remain completely unexplained. With no enrichment from the description, the agent cannot correctly construct arguments.
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 ('Move'), identifies the resource ('an active run'), and states the destination ('a local awaiting-human lane'). It clearly indicates the core operation. It does not explicitly differentiate from siblings like raise_attention, but the core action is understandable.
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 is provided on when to use this tool versus alternatives such as raise_attention, respond_intervention, or list_pending_reviews. The description implies the run must be active and the result is local, but it does not state prerequisites, exclusion conditions, or which sibling tools should be chosen instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.