审核工单

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

Beyond the destructiveHint annotation, the description discloses a critical behavioral trait: agreeing at the final step triggers SQL execution, and it explicitly labels agree as high-risk. This adds important consequences that annotations alone do not convey.

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, well-structured sentence packed with essential operational details. It uses punctuation effectively to separate actions and conditions, with no wasted words.

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 covers the key behavioral aspects needed to use the tool correctly: actions, prerequisites, risk, and confirm requirement. Since there is no output schema, return values are not explained, but the description is sufficient for safe and correct invocation.

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?

Although the schema already describes all parameters (100% coverage), the description enriches the flag parameter with cross-tool usage (use yearning_order_timeline to confirm) and clarifies that reject requires a reason. This adds meaning beyond the raw 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 clearly states the tool audits work orders with three specific actions (agree, reject, undo) and even mentions the corresponding API endpoint. It distinguishes itself from list-oriented siblings like yearning_audit_orders by focusing on state-changing operations for a single order.

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 concrete guidance: use yearning_order_timeline to confirm the current step (flag), provide a reason when rejecting, and set confirm=true for agree. It gives clear context for when to use the tool, though it does not explicitly contrast with alternative tools like yearning_undo_order.

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