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

Goes well beyond the readOnly/destructive annotations by disclosing that output is UNSIGNED tx data (to, data, value, gas), that it is simulated against the latest block and refused if it would revert, and that it never signs or sends. The path-selection windows (maxSettleLag, +7 days) are behavior an agent cannot infer from any structured field.

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?

Front-loads the 'After expiry' precondition and then packs rules efficiently with no filler sentences. It is a single dense paragraph, which is slightly harder to scan than bulleted branches would be, but every clause carries real information.

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?

With no output schema, the description supplies the return shape, the simulation/refusal semantics, and the self-custody boundary (never signs or sends). Combined with the schema, an agent has everything needed to call it and interpret the result.

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%, so both `market` and `from` are already documented. The description adds the derived roundId concept used to build the proof, which is useful, but does not clarify the market symbol/address handling or the guardian-safe override beyond what the schema already states.

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+resource (build the settle transaction) and describes the mechanics precisely: first Chainlink round at/after expiry, proof encoded as abi.encode(uint80 roundId), and the three possible call targets. It never distinguishes itself from the sibling prepare_mandate_settle, so an agent can't tell which of the two settle-preparation tools fits a mandate account.

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?

Explicit timing gates ('After expiry', 'Refused before expiry, once settled, and until the round has printed') and a clear fallback ordering between settle, guardianSettle, and settleBackstop tell the agent exactly when this applies. It stops short of naming the alternative sibling to use when these conditions fail.

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