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

Annotations only supply readOnlyHint and openWorldHint; the description goes far beyond them by disclosing the data provenance ('goplus+onchain'), determinism ('no LLM'), the exact return shape via a sample JSON, and a non-obvious operational requirement — a $0.009 USDC x402 payment passed in _meta['x402/payment']. That payment requirement is critical and would be missed without the description.

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?

Purpose and risk list come first, then usage trigger, then determinism, then the concrete sample output, then price. The sample JSON is long but earns its place because there is no output schema, and it resolves return-shape questions in a single glance.

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?

With no output schema, the embedded example supplies the full response contract (riskScore, verdict, flags, tax fields, holder stats, source). Combined with chain coverage, determinism, and payment mechanics, an agent has everything needed to call this correctly and interpret the result.

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%, and the schema already documents both the chain enum (base default, ethereum, arbitrum, optimism) and the address field. The description restates the supported chains and shows an address in the sample output, but adds no new semantics such as whether checks differ per chain or what happens for unsupported tokens. Baseline 3 applies.

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 ('Scam check for an ERC20'), then enumerates exactly which risks it detects (honeypot, tax, mintable, proxy, blacklist, holder concentration, LP lock) and which chains. An agent can immediately distinguish it from siblings like base_token_info or token_price, which do not assess risk.

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 an explicit trigger: 'Use before buying or accepting a token.' That is a clear usage context with no ambiguity. It stops short of naming alternatives (e.g., 'use base_token_info for plain metadata'), so there is no exclusion guidance, but the intended moment of use is unambiguous.

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