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

While annotations confirm it is readOnly, the description adds critical operational behavior such as the specific cost of execution, which is a major behavioral trait. It also notes that failures are free and repeats incur a cost, adding necessary economic context.

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 highly dense and efficient. It manages to communicate purpose, usage, operational constraints, cost, and sibling comparison in a single, well-structured paragraph without unnecessary filler.

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?

This is an exceptionally complete definition. It covers what the tool returns (raw amount, decimals, human-readable amount), its operational cost, its failure modes, its limitations, and its relationship to other tools.

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?

Although the schema covers the parameters, the description adds crucial semantic detail by explicitly stating that both input parameters must be 0x addresses consisting of 40 hex characters, thereby clarifying the required format beyond the generic 'string' type.

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 clearly defines the tool's function (ERC-20 token balance on Celo) and provides a direct differentiation from the sibling tool celo_balance (for native coin). This explicit comparison leaves no doubt about which tool to use.

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?

It not only suggests when to use the tool (before a transfer or trade) but also provides highly specific operational guidelines, including error code behavior (404, 422), cost structure ($0.01/call), and free usage limits.

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