decision_createCreate decision proposals by assembling trigger conditions, judgment logic, conclusion, recommended actions, and evidence. Use for review and approval without executing any external action.
按触发条件、判断逻辑、系统结论、建议动作和证据创建提案。该工具不会执行外部动作。
| Name | Required | Description | Default |
|---|---|---|---|
| logic | Yes | ||
| trigger | Yes | ||
| review_at | No | ||
| conclusion | Yes | ||
| project_id | Yes | ||
| evidence_ids | No | ||
| execution_mode | No | human_approval_required | |
| recommended_action | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds one behavioral note: '该工具不会执行外部动作' (this tool does not execute external actions), which is useful beyond the annotations (all false). However, it does not disclose other behaviors like what happens to existing data or whether the proposal is persisted, so the value added is limited.
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 two sentences with no fluff, front-loading the core purpose before the behavioral note. It is appropriately concise for its length.
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 tool with 8 parameters, 5 required, no output schema, and no annotation support, the description is too thin. It lacks details on parameter meaning, execution_mode options, review_at usage, and expected outcomes, making it incomplete for an agent to call 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?
Schema description coverage is 0%, so the description must compensate. It names five components (trigger, logic, conclusion, recommended action, evidence) which map to trigger, logic, conclusion, recommended_action, and evidence_ids, but it does not explain project_id, review_at, or execution_mode. With 8 parameters, this is insufficient.
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 clearly states the verb '创建' (create) and resource '提案' (proposal), and enumerates the key components (trigger, logic, conclusion, recommended action, evidence). However, it does not explicitly distinguish from sibling tools like decision_review or decision_list, so it falls short of a 5.
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 provides no guidance on when to use this tool versus alternatives such as decision_review or decision_list. It only states what the tool does, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.