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

With no annotations, the description carries full burden and does so well: it discloses that it accepts no transaction authority, verifies reviewed program-owned accounts, simulates the full unsigned message, checks both assets' oracle evidence, verifies the submitted mint against the live SPL account for Save, and returns ALLOW/CAUTION/BLOCK. The PriorSeal post-condition clarifies what an ALLOW does not authorize.

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 scope and the exact-one-instruction constraint are front-loaded, and most sentences add value. It is dense and slightly run-on, but no sentence is 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?

Given a complex nested schema, no annotations, and no output schema, the description covers the safety profile and the return verdicts (ALLOW/CAUTION/BLOCK). The main gap is that it does not explain the guard context fields (USD values, symbols) an agent must supply.

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% and parameters are deeply nested, so the description must compensate. It adds meaning for the transaction (exactly one direct instruction) and the assetMint behavior for Save, but does not explain the guard fields (collateralValueUsd, debtValueUsd, action) or the transaction structure beyond the single-instruction constraint.

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 resource ('Create portable Insight risk evidence') and bounds it to 'exactly one unsigned direct Kamino Lend, Marginfi v2, Jupiter Lend Earn deposit, or Save Lend reserve-liquidity deposit instruction on Solana mainnet.' This clearly distinguishes it from siblings like base_lending_guard, multichain_evm_lending_guard, and loopscale_vault_deposit.

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?

Gives clear conditions: exactly one unsigned direct instruction on mainnet across four named protocols, and notes an ALLOW still requires a separate user-authorized PriorSeal binding before execution. It does not explicitly name the alternative to use for the excluded protocols (e.g., loopscale-vault appears in the enum but not the prose), leaving some routing inference to the agent.

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