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

With no annotations to lean on, the description carries the full behavioral burden and does so: it enumerates exactly what is verified (target, selector, token/market binding, sender, nonce, zero value), describes the return artifact (short-lived EIP-712 decision, conditional on Insight signing being configured), and states hard limits ('never authorizes, signs, or broadcasts'). The conditional signing requirement and the required external ALLOW binding are non-obvious traits an agent could not get from the schema.

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, each load-bearing: what is produced, what is checked, and what it does not do. Dense with domain jargon but front-loaded and free of filler; the final sentence about PriorSeal is essential rather than padding.

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?

A verification/attestation tool with a nested schema, zero parameter descriptions, and no output schema needs more: it never says what happens on a failed verification (error shape, reason codes), how long 'short-lived' is, or how the USD amounts feed the risk model. Enough to call it correctly in outline, not enough to interpret results.

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% on a nested two-object schema, so the description must compensate and only partly does: 'target, selector' map to transaction.to/data, 'token or market binding' to collateralSymbol/loanSymbol/marketId, and 'sender, nonce and zero value' to from/nonce/value. The guard's collateralValueUsd and debtValueUsd, the protocolId/action enums, and chainId being fixed at 8453 are never explained in prose.

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 and artifact ('Create portable Insight risk evidence') for a precisely scoped resource: one exact unsigned direct supply/borrow call on Aave V3, Morpho Blue, Compound V3, or Moonwell on Base. The 'one exact ... call' framing implicitly separates it from the broader sibling base_lending_guard and from monad_lending_guard_exact_call, so an agent can route without reading schemas.

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?

It establishes the usable context (you must already have an exact unsigned transaction plus guard intent) and the downstream step: 'bind an ALLOW through PriorSeal or another user-authorization system.' It does not explicitly say when to choose this over base_lending_guard or pre_trade_safety_check, so alternatives are left to inference.

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