Escalate the job to a human. Use when you cannot resolve an issue, someone is not responding, or a situation requires human judgment.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | No | Omit it: the run's own job is used. Never pass a thread or message id here. | |
| reason | Yes | Why escalation is needed | |
| in_workspace | No | Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected. |
Changes observed during successful MCP inspections.
Input schema / properties / in_workspaceAdded value: +{
+ "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
+ "type": "integer"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (not read-only, not idempotent, not destructive, closed-world), lowering the bar. The description says when to escalate but nothing about what escalation actually does mechanically (notify whom, whether the job pauses, reversibility, latency), which is meaningful missing context for an action 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?
Two short sentences, purpose front-loaded, no filler. Every clause either states the action or the condition for using it.
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 low-complexity action tool with one required param, full schema coverage, and no output schema, the description adequately conveys purpose and trigger conditions. It could be stronger by clarifying the effect of escalation or contrasting with agent_handoff, but nothing essential to calling it correctly is missing.
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 100%, including useful constraints like omitting job_id to default to the run's own job and not passing thread/message ids. The description adds no parameter-level meaning beyond what the schema already provides, so the baseline 3 applies.
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?
States a specific verb and resource ('Escalate the job to a human'), so the agent knows exactly what action is performed. However, it does not differentiate itself from plausible siblings such as agent_handoff or agents_ask, which also route work elsewhere, so the boundary is left to inference.
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?
Gives clear triggering conditions ('when you cannot resolve an issue, someone is not responding, or a situation requires human judgment'). It does not name an alternative tool or state when NOT to escalate, so it stops short of explicit routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.