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

The description provides rich behavioral context beyond the `readOnlyHint: true` annotation. It details pricing models ($0.01/call, first 25 free), transaction failure codes (404, 422), and confirms it is a read/compute operation. This adds significant value to the agent's decision-making process.

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 dense but highly efficient. While some sentences are slightly long, every clause adds critical information regarding function, scope, and cost, making it context-rich without being verbose.

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 inclusion of sibling tools and a clear parameter set, the description provides all necessary information regarding usage, constraints, failure modes, and operational costs, making it fully complete for the AI to invoke 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 the baseline is high. The description adds valuable semantic context to the `token` parameter, explaining it can be a ticker (USDC) or a 0x contract address, which clarifies input expectations beyond just the 'type: string' in the schema.

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?

Explicitly states it checks the ERC-20 token allowance and specifies what information is returned: raw/token units and unlimited status. It also differentiates itself by mentioning that `mantle_token_balance` should be used for simple balances.

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?

Provides extremely clear use cases: check approval before a swap or for auditing risky open approvals. It also provides crucial usage context regarding failure codes (404, 422) and pricing (first 25 free). It implicitly excludes standard balance checks via `mantle_token_balance`.

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