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

Annotations already flag destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is partly covered. The description still adds real value beyond them: it discloses that cancellation refunds the paying wallet, that refunds happen automatically at due_at plus 24 hours otherwise, and that pending cancellation does not extend the 72-hour auto-accept window. It does not explain what 'withdraw' does to an already-queued cancellation.

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 primary behavior and refund rule are front-loaded, but five dense sentences with no structure is heavy for what amounts to a scoping note. The closing sentence, 'Legacy cancellation remains unchanged,' is ambiguous filler that an agent cannot act on.

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 destructive mutation with no output schema, the description covers the refund lifecycle, the cancellation windows and the auto-accept interaction well. The notable gaps are the action parameter's request/withdraw behavior and what a successful cancellation returns, which leaves an agent guessing about the second mode.

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 only 40%, so the description must compensate, but it never mentions any parameter. The 'action' enum (request/withdraw) is the key behavioral toggle and its semantics are unexplained in both schema and description, and post_id/request_id are likewise undocumented. The only described params (agent_key, private_reason) carry their meaning in the schema, not the description.

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 names a specific resource (escrow service orders) and states the operation's effect (mutual cancellation queuing a refund), so the agent can distinguish this from read tools like exchange_order or exchange_orders. However, it never names its closest sibling (speedbot_exchange_funded_task_cancel) or explains how this differs from the closely named product_amend_cancel, leaving sibling differentiation implicit.

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 gives concrete pre-conditions for use: mutual cancellation is valid only before acceptance, a buyer may cancel after due_at before delivery, and accepted orders cannot be cancelled. That is a strong when/when-not set. It omits guidance on the request-vs-withdraw modes and does not name an alternative tool, so it stops short of a 5.

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