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

The description transparently states that every call persists an immutable Merkle-anchored snapshot, which is a side effect an agent should know. It also clarifies the limitation of 'no-loans-ever' (not proof of none) and the risk of borrowers erasing defaults. However, it does not explicitly state whether the tool is read-only or has any destructive capabilities, though the snapshot mention implies a write. The description is largely transparent about behavioral nuances.

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 description is dense but well-structured. It front-loads the main purpose, then provides important caveats, return value hints, and operational notes. All sentences contribute value—some are warnings, some explain state meanings, and some clarify the mainnet status. No fluff or redundancy.

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?

The description covers all essential context: what the tool does, what it returns (outstanding by asset, loan count, etc.), the meaning of disposition states, mainnet status, and a disclaimer. It also mentions the free pricing. Given there is no output schema, the description compensates by listing return fields. No critical missing information for an agent to decide to call this tool.

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?

The parameter 'borrower' is described with details: XRPL classic address format (r..., 25–35 chars) and required status. This matches the schema. The description adds contextual value by explaining the address format and the required constraint, but there is only one parameter and no enums or nested objects, so the coverage is adequate. A small deduction because the description does not elaborate on possible edge cases (e.g., invalid address handling), but it is clear enough.

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 clearly states the tool's purpose: to retrieve a borrower's total XLS-66 lending exposure across all loan brokers. It specifies the resource (borrower exposure data) and the action (get). It also differentiates itself from a sibling tool (get_lending_history) by focusing on aggregate exposure across brokers, which is distinct.

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 description provides explicit guidance on when to use this tool: when needing total lending exposure across all brokers. It also includes important caveats about XLS-66 not being enabled on mainnet, the meaning of 'disposition' values, and the fact that deletions can erase default evidence. This is actionable guidance for an agent.

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