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

Annotations already flag this as destructive and write-oriented. The description adds valuable behavioral context beyond annotations: the financial outcome (90% to seller, 10% platform fee) and that the buyer initiates escrow release. This helps the agent understand the irreversible financial impact.

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 concise sentence, front-loaded with the '[Buy]' category. Every word adds value, including the percentage split, and there is no wasted text.

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 simple one-parameter tool with clear annotations, the description covers the essential outcome and actor. It lacks explicit failure handling or prerequisites, but the simplicity and annotations make it adequate. It is more complete than a bare mutation description.

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 coverage is 0% and the description does not mention the purchaseId parameter. The parameter name is self-explanatory, but the description provides no additional meaning or format guidance, leaving the agent with minimal information about this required input.

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 function: the buyer releases escrow, with proceeds split 90/10 between seller and platform. This is a specific action tied to the tool name, and it distinguishes itself from siblings like dispute_purchase or ack_purchase.

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 implies usage: the buyer confirms delivery to release escrow. However, it does not explicitly contrast with alternatives or state when not to use it. The context is clear but not formalized with exclusions or alternative guidance.

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