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

Annotations already declare readOnly, non-destructive, open-world, non-idempotent; the description adds pricing ($0.01/call, 25 free), that failed calls are free, and that repeats are not free — which explains the otherwise puzzling idempotentHint=false on a read. It does not mention caching or latency, a minor gap.

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 how to use it, then pricing and error semantics. Dense but every sentence carries information; the final sentence bundles read-only, charge, and repeat-nonfree facts a bit tightly.

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?

No output schema exists, yet the description enumerates the returned fields (name, symbol, decimals, total supply) and covers the single input's two forms, error behavior, and cost — everything needed to call 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%, so baseline is 3; the description adds that a bare ticker is accepted as well as a 0x address and supplies a worked example address, clarifying input flexibility beyond the schema's one-liner.

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 ('Look up the name, symbol, decimals and total supply of an ERC-20 token contract on Arbitrum One') and scopes it to a chain, so it is clearly distinguishable from the dozens of sibling *_token_info tools.

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 both positive use cases (identify an unknown token address, format raw amounts) and an explicit alternative with its condition ('for a holder's balance use arb_token_balance'), plus the failure case (non-ERC-20 address returns 422).

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