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

With no annotations, the description carries the full behavioral burden and does real work: it discloses that escrow is frozen, that both parties then submit evidence, and that an AI panel makes the split decision. It stops short of stating whether the freeze is irreversible, what costs or deadlines apply, or what the caller receives back.

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?

Two tight sentences, zero filler, and the most important consequence (escrow freeze) is front-loaded before the downstream process. Nothing repeats the schema or annotations.

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 three-parameter mutation with no annotations and no output schema, the description explains the lifecycle but omits the risk profile an agent would want: whether the dispute is final once opened, whether it can be withdrawn, and what response to expect. Adequate but with clear gaps given the zero annotation coverage.

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 100%, so deal_id, token, and reason are already documented in the schema, including the token's origin and the expected reason format. The description adds no additional parameter meaning beyond that baseline.

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 conveys the concrete effect of opening a dispute: escrow is frozen, both sides submit evidence, and an independent AI panel decides the split. It distinguishes the action from siblings like mm_add_evidence and mm_respond_to_ruling by describing the phases, though the action verb itself lives in the name/title rather than the description.

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?

Usage is only implied — one infers this is the escalation path when a deal goes wrong, reinforced by the 'reason' parameter. There is no explicit statement of when to choose this over mm_refund_buyer, mm_cancel_deal, or mm_respond_to_ruling, and no stated prerequisites such as being a party to the deal.

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