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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds substantial context on top: errors are rejected with 400 and uncharged, the first 25 calls are free, failed calls are free, each successful call costs $0.01 via x402 or a card key, and repeats are not free despite being safe. That pricing and error-charging behavior is exactly the kind of trait annotations cannot express.

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?

A single dense paragraph that front-loads the scope (wallet, token, window, result shape) before usage, errors and pricing. It is long but almost every clause carries a distinct fact; the only waste is mild redundancy between 'first 25 free / failed calls free' and the closing 'each call is charged, so repeats are not free.'

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?

For a 3-parameter read tool with no output schema, the description covers everything an agent needs: what is returned and in what order, the result cap, the address format with an example, the failure mode and its cost, and the billing model. No material gap remains.

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 schema already documents token, blocks range/default and address, and the description largely repeats it (default USDC, 1-2,000 blocks, default 1,000). The one genuine addition is a worked address example (0xd8dA...6045) showing the expected 0x format, which is useful but marginal against a fully documented 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?

States a specific verb and resource (list recent ERC-20 transfers for one wallet on Avalanche) plus the exact shape of the result: in/out, direction, counterparty, amount, transaction, newest first, capped at 50. It also pins the default token (USDC) and the block window, so an agent can distinguish it from avax_token_balance and from the other per-chain transfer tools without opening the schema.

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 an explicit use case (confirm a payment arrived or see what was sent) and names the alternative with the condition that selects it: 'for the current balance use avax_token_balance.' Nothing about when-to-use is left to inference.

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