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

Annotations already declare readOnlyHint and idempotentHint, and the description adds useful behavior beyond that: it returns both raw and formatted values, reads decimals on-chain with a labeled common-list/18 fallback, and preflights calls so the user avoids paying during an RPC outage. This is meaningful transparency for an RPC-backed read.

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 description is two sentences with no fluff. The core function is front-loaded, and the parenthetical about decimals plus the preflight note both earn their place by adding decision-relevant behavior.

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?

Given the output schema and annotations, the description is largely complete: it covers the token contract scope, decimals behavior, formatted results, and cost protection. It could be slightly fuller by mentioning supported networks or explicit exclusions, but none are critical for an ERC-20 balance lookup.

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?

The input schema already covers all parameters with 100% description coverage, so the description does not need to repeat parameter semantics. It adds slight context around decimals fallback via the phrase 'common-list/18 fallback is labeled,' but this mostly mirrors the schema's decimal override description.

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 description states a specific verb and resource: 'Raw + formatted ERC-20 balanceOf for an address at any token contract.' This clearly differentiates the tool from generic balance checkers like balance_check by scoping it to ERC-20 tokens at a specified contract address.

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?

The description implies the use case: retrieve an ERC-20 token balance for a holder address at a particular token contract. It does not explicitly name alternatives or state when not to use the tool, though the ERC-20 scoping provides some context against sibling tools.

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