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

The description provides significant behavioral context beyond annotations, detailing what is returned (confirmed, unconfirmed, total received/sent/counts) and crucial operational details (pricing, failure costs, read-only nature). The annotation readOnlyHint: true reinforces this, but the description adds necessary details about the call cost and idempotent nature.

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 definition is highly descriptive, which is necessary for a tool covering multiple sub-metrics (balance, unconfirmed, sent, received). It is structured logically, starting with the service provided and ending with operational constraints.

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?

The description is highly complete, covering input requirements (address format), output scope (types of balances), and critical operational metadata (cost structure, id/mutability). No significant gap exists for an AI agent.

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 a baseline of 3 is met. The description reinforces the required format and nature of the 'address' parameter, specifying which mainnet types are accepted (legacy, P2SH, bech32).

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 name (btc_address) combined with the title and description clearly specifies the action (check balance and transactions) and the resource (Bitcoin 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 provides explicit use cases ('payment verification, checking whether a deposit arrived, and wallet monitoring') and clarifies the scope (mainnet addresses only).

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