safety_policy

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the tool is read-only, which is a key behavioral trait. It also clarifies the downstream behavior (direct execution vs. preview) based on the returned policy, adding useful context beyond a simple read operation. However, it does not mention potential side effects or error behavior, though since it is read-only, this is a minor gap.

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 compact sentences. The first sentence front-loads the core purpose and fields, and the second sentence provides essential usage guidance. There is no redundancy or filler; every sentence provides valuable information.

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 description sufficiently covers the tool's role as a policy gate at session start, and it explains the auto_approve logic that connects to sibling preview/apply tools. The output schema exists, so not detailing return values is acceptable. However, it assumes the reader knows what 'domains' mean in the policy context, which could be ambiguous without broader system knowledge.

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?

The tool has zero parameters, so the description does not need to explain parameter semantics. The baseline for zero params is 4, and the description adds no unnecessary parameter information, which is appropriate.

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 tool's purpose: '只读返回当前安全策略' (read-only returns the current safety policy) and explicitly lists the fields (mode/allow_rules/deny_rules/auto_approve). This distinguishes it from sibling tools, which are action-oriented preview/apply operations, making the purpose unambiguous.

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 explicit usage context: '会话开始时先调用本工具' (call this tool first at session start). It also explains the decision logic—auto_approve matching domains can be executed directly, while non-matching domains require preview and user confirmation—which guides when to use this tool versus relying on preview tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.