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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds real value beyond them: the whole operation runs in one Serializable transaction, and the cancel leg is hosted-authoritative with no broadcast and no maker gas owed. It does not say what happens when the placement leg fails mid-transaction or whether an idempotency retry replays a prior success — notable given idempotentHint=false alongside a required idempotencyKey.

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: the atomic all-or-none contract leads and the hosted-cancellation consequence follows. No padding, though the second sentence's gas/broadcast note could be folded into the first without loss.

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?

Output schema exists and annotations cover the destructive profile, so return values and safety need no prose. Still missing for a destructive, non-idempotent mutation: failure modes for the all-or-none path, the role of suspendOrderHashes, and explicit routing against the batch and single-order siblings.

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?

At 44% schema coverage across 9 parameters, the description should be compensating, but it names no parameter at all. 'The named old orders' only loosely gestures at suspendOrderHashes (an undescribed, defaulted array) and 'signed post-only successor' implies orders[].postOnly/orderSignature, while the wallet proof, proofNonce and idempotencyKey auth contract is left entirely to the schema.

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 compound verb and resource — 'hosted quote replacement for one wallet/chain/market' that 'terminally cancel[s] the named old orders and place[s] every signed post-only successor' — so the effect is unambiguous. The singular scope also implicitly separates it from problee_batch_replace_quote_sets, though that sibling is never 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?

The 'all-or-none' framing implies this is the tool for a coordinated cancel-and-replace rather than a lone problee_place_limit_order or problee_cancel_order, but no alternative is ever named and no when-not condition is given. An agent must infer that setUp replacement across multiple markets belongs to a batch sibling.

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