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

Goes well past the annotations: it declares the effect terminal, states there is nothing to broadcast and no gas owed, and explains the non-obvious exception that orders with committed taker reservations are suspended and settle later. It also flags pagination and the wallet-proof requirement, which the destructiveHint alone would 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?

Three tight sentences, front-loaded with the terminal/no-gas guarantee that matters most. Every sentence carries information, though "on the page" is a small source of ambiguity that could be trimmed.

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?

Covers scope, side effects, the taker-reservation edge case, pagination, and the auth proof requirement for a 9-parameter destructive tool, and an output schema exists so return values need no explanation. It could still say whether a separate confirm step is ever required.

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 78%, so the schema already documents most parameters including the market filter and proof nonce. The description adds only the mapping of "optionally scoped to a market" and "paged" to the filter and cursor arguments, without new format or constraint detail.

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?

States a specific verb and resource ("cancel every open order") plus a concrete layer ("at the hosted layer"), which separates it from on-chain cancellation siblings. The phrase "on the page" muddies scope by suggesting page-local cancellation, and no sibling such as problee_cancel_order or problee_confirm_order_cancel is named.

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 implied through "optional market scoping" and the terminal/hosted nature, which hints no confirmation round-trip is needed. It never says when to pick this over problee_cancel_order, problee_cancel_orders, or problee_confirm_order_cancel, so an agent must infer the choice.

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