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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description still adds substantial context beyond that: addresses are UUPS/stable, approvals are one-time and engine-scoped, they will 'drop out' as approval-free sells ship, and a settlement-committed collateral emits no approval at all. That is meaningful lifecycle and data-stability information an agent could not get from annotations alone, though it is delivered as dense prose rather than structured caveats.

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?

One enormous run-on sentence with em-dash-nested parentheticals, followed by several loosely connected assertions about settlement ledgers, creator roles, and human identity. The key fact (what you get back) is front-loaded, but the remaining text is bloated and would take several reads to unpack; the final sentence about human identity services reads as tangential.

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?

An output schema exists, so return shape need not be explained, and the description does cover the substantive semantics (which collaterals need approvals, which emit none, role/creation flags). Missing is any statement of the tool's own call behavior — e.g. what happens when chainId is omitted versus filtered — leaving the description rich in domain lore but incomplete on invocation.

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 100% and the two optional filters (chainId, collateral) are fully documented in the schema. The description never mentions either parameter or how filtering interacts with the per-chain/per-collateral results, so it adds nothing over the schema — baseline 3.

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 opening clause names the resource concretely (per-chain collateral addresses, MarketRouter proxies, OutcomeToken1155, factories, and required approvals), which is genuinely distinguishable from siblings like kellian_list_collateral. However, the sentence immediately dissolves into approval mechanics and caveats, so the core 'this returns contract addresses plus required token approvals' purpose is buried rather than stated crisply.

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?

There is real guidance embedded ('check the actual /trade/prepare or /trade/simulate response for one market rather than assuming this list is permanent', 'Creator agents must select a collateral with creation=true', 'Cancel and direct market-local claims need no approval'), but it is written as scattered mid-sentence asides rather than explicit when-to-use/when-not-to-use. No sibling is named as an alternative, so the agent must infer routing from domain jargon.

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