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

With no annotations, the description carries the full burden and does reasonably well: it discloses the paid x402 flow ($0.01 USDC on Base), and crucially discloses a coverage limitation — the buy→sell round-trip simulation only runs on six of the eight chains, with no simulation mentioned for Avalanche or Solana. It does not state latency, rate limits, or whether a failed simulation yields partial results, which keeps it below a 5.

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?

Two sentences, front-loaded with the action and its scope, and the second sentence adds a genuinely distinct capability rather than repeating the first. The chain enumeration is long but earns its place given the parameter enum; a slightly tighter phrasing could have listed the simulation-supported chains once.

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?

For a tool with no output schema and four parameters, the description effectively previews the report contents by enumerating every audited dimension, which is what an agent needs to judge relevance. The main gap is that it doesn't distinguish paid vs free paths or indicate what a partial/failed audit looks like.

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 100%, so the baseline is 3 and the schema already explains chain defaulting, address formats, and the default order size. The description adds only modest value, explaining that intendedOrderUsd drives AMM slippage estimation, but it says nothing about paymentSignature or what happens if payment is omitted.

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?

Specific verb (audit) plus resource (token contract) with an explicit enumeration of the checks performed: honeypots, taxes, hidden ownership, whale concentration, LP locks, liquidity depth, slippage. The supported chain list is spelled out, so an agent knows exactly the scope without opening the schema. Clearly differentiated from generic lookups like chain_token_info.

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?

Usage is implied by how specific the checks are — you reach for this when you need safety/due-diligence analysis rather than a plain balance or metadata lookup. However, it never says when NOT to use it or names an alternative sibling (e.g. chain_token_info) for simpler needs, and it doesn't state prerequisites such as needing a funded payment for x402.

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