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

Goes well beyond the readOnly/openWorld annotations: discloses per-call pricing ($0.002 via x402, USDC on Base, MCP payments Base-only), that found:false is a billed answer, that bad input or RPC outage is unbilled on Base but other rails may charge, and a security caveat that returned names/symbols are untrusted third-party data. The buyer-terms link and payment rail constraint are exactly the kind of operational context annotations cannot carry.

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?

Front-loads what is returned and the chain-state exclusion, then moves to billing and trust caveats in roughly priority order — all sentences carry information. It is a dense semicolon-chained run-on, which slightly hurts scanability but wastes almost nothing.

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 description carries the burden and does: it enumerates the returned fields per chain, explains the found:false sentinel, and covers cost, billing exceptions and data-trust. An agent has everything needed to call it, interpret a miss, and predict the charge.

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 both parameter descriptions already state the accepted formats (0x address / mint address / CURRENCY.rIssuer; network list or CAIP-2). The description's restatement of 'network and token (0x address, mint, or CURRENCY.rIssuer)' adds little beyond the schema, so the 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?

Names a specific verb+resource (token metadata) and enumerates exactly what is returned per rail: ERC-20 name/symbol/decimals/total supply on Base/Polygon/Ethereum, Solana mint decimals/supply/authorities (Token-2022 name+symbol), XRPL supply/issuer flags/transfer fee. The closing 'Chain state only: no price, no token-list check' explicitly separates it from price/quote siblings like market_quote and from token-list checks.

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 positive conditions (chain state for a given network+token, three address formats) and negative exclusions ('no price, no token-list check'), which steers the agent away from misusing it as a price oracle. It stops short of naming the alternative sibling tools explicitly, so it is strong but not a full when/when-not/alternatives statement.

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