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

Annotations already cover read-only/idempotent/non-destructive/open-world, and the description adds a great deal on top: verdict semantics (GO/REVIEW/STOP), a fail-safe rule ('A vector that could not be read is unknown, never clear'), and invocation economics (x402 on Base, $0.06/call, prepaid header for unlimited, 1 free call/day, no API key). Cost, auth and rate-limit behavior are all disclosed, which is exactly the beyond-annotation context that matters.

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 purpose, vectors and routing rule are front-loaded and each of those sentences earns its place; payment/auth details are also load-bearing for a paid x402 tool. It runs long as a single undifferentiated block and the 'Not financial advice' boilerplate is filler, keeping it out of the top band.

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?

An output schema exists, so return values need no explanation, yet the description still names the verdict vocabulary. Combined with the covered vectors, fail-safe behavior, cost and auth model, an agent has everything needed to decide to call it and to invoke it correctly.

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% for the single 'wallet' parameter, so the schema already carries the burden and 3 is the baseline. The description only restates it ('Required input: wallet') without adding format guidance (address vs ENS, required chain scope), so it adds no meaning beyond the schema.

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 opening states a specific, vivid verb+resource: 'The three ways an agent wallet gets emptied, in one verdict,' then enumerates the exact vectors (EIP-7702 delegation, Base Account spend permissions, ERC-20 approvals). It explicitly positions itself against siblings by naming the tools it composes ('wallet-delegation + spend-audit + approval-advisor ... in one call instead of three'), so an agent can distinguish the aggregate from the individual scanners.

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 states the selection rule directly: use this to check the whole surface in one call rather than three, and 'drill into each vector for detail' when per-vector depth is wanted. Both the when-this and the when-the-alternatives conditions are explicit, so no inference is required.

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