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

The description goes far beyond the annotations by detailing critical business consequences that a simple write operation hint misses, such as prices being 'freeze[d]' and the subsequent lifecycle restrictions (can only be received, closed short, or cancelled). This provides vital behavioral context for the agent.

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?

While slightly verbose, the description is highly effective. It front-loads the core definition and then organizes the remaining sentences logically: consequence, trigger, restriction, and final effects. It earns its length by providing necessary business logic.

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?

Given the inherent complexity of a state-transition tool in a procurement workflow, the description is exceptionally complete. It defines the action, the trigger for the action, and all the resulting behavioral constraints on the order object.

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?

With 100% schema description coverage, the parameters are fully documented in the schema itself. The description correctly identifies the requirement for an existing PO ID but adds no semantic value regarding the input beyond what is already specified in the structured data. Baseline score 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 defines the action as recording that an order has been officially sent to the vendor, which clearly distinguishes it from creation tools (like p2p_create_po) and reception tools (like p2p_goods_received). It focuses on a specific point in the PO lifecycle.

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?

It provides extremely clear usage guidelines by specifying the exact trigger: 'Issue when the person says the order went out.' It also clearly defines the 'when not' conditions by stating that after issuing, the order cannot be edited.

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