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

With no annotations, the description carries the full burden and does well: it declares read-only semantics, enumerates the three possible verdicts, states the evidence basis (live protocol state plus independent oracle evidence), and gives per-protocol acceptance constraints such as Euler's four-step EVC batch and Fluid's collateral-only supply. It leaves out failure behavior for unsupported chain/protocol combinations and any rate-limit or auth expectations.

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 sentences, front-loaded with the core purpose and verdict contract, then protocol-specific exceptions. The protocol roster sentence is dense but each clause carries constraints an agent needs; nothing is redundant filler.

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?

Behavior and output contract are covered well, and the lack of an output schema is offset by the ALLOW/CAUTION/BLOCK statement. However, for a 13-parameter, 7-required tool with zero schema descriptions and no annotations, the absence of any per-parameter guidance (especially the protocol-dependent identifier fields) leaves a meaningful gap.

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 description coverage is 0% across 13 parameters, so the description must compensate — and it barely does. 'Caller-declared post-action values' hints that collateralValueUsd/debtValueUsd are projected post-action figures, but marketId, loanMarketId, collateralMarketId, accountNumber, marketAddress, and collateralVaultAddress are entirely unexplained in both schema and description.

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: a read-only pre-signing gate that checks caller-declared post-action values against live protocol state and returns ALLOW/CAUTION/BLOCK, scoped to named chains and protocols. The chain/protocol enumeration implicitly separates it from base_lending_guard, monad_lending_guard, solana_lending_guard and the _exact_call sibling, but no sibling is named explicitly.

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 'pre-signing gate' framing and 'never signs, broadcasts, or authorizes' clause make the use context clear, and the Euler/Dolomite/Fluid eligibility rules tell the caller which input shapes are accepted. It stops short of naming alternatives (e.g. when to prefer the base-only or exact-call guards), so it falls short of a 5.

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