Resolve pending human-in-the-loop checkpoints by approving, rejecting, or aborting them. Provide an optional comment to document your decision and control AI agent workflow progress.
对挂起等人工确认的 checkpoint 提交决策（approve/reject/aborted）。
| Name | Required | Description | Default |
|---|---|---|---|
| comment | No | 可选备注（如驳回原因） | |
| decision | No | 人工决策（必填） | |
| checkpoint_id | No | HITL checkpoint ID（必填） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses that this is a decision-submitting action on a pending checkpoint and lists the three possible outcomes. However, it does not explain the downstream effects of each decision, whether the action is reversible, or what 'aborted' semantically implies, leaving meaningful gaps.
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?
A single front-loaded sentence states the action, the target state, and the allowed decisions with no redundant wording. Every part earns its place.
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 tool is low-complexity and the schema covers all parameters, so the description is adequate for basic invocation. However, with no output schema and no annotations, it omits what happens after a decision is submitted, whether the decision is final, and any failure or prerequisite conditions beyond 'pending'.
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%, so the parameters are already well documented in the input schema. The description adds only the overall HITL context and reinforces the decision enum, but does not materially deepen understanding of checkpoint_id, decision, or comment beyond the schema.
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 states a specific verb and resource: submit a decision for a HITL checkpoint, and enumerates the allowed decisions (approve/reject/aborted). This clearly distinguishes it from sibling tools, none of which overlap with HITL checkpoint resolution.
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 scopes the tool to '挂起等人工确认的 checkpoint' (pending checkpoints awaiting human confirmation), which gives a clear condition for when to use it. It does not explicitly name alternatives or exclusion cases, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.