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

In the absence of annotations, the description carries a heavy responsibility and carries it well. It discloses the IP-blind behavior through the proxy, openly acknowledges the relay-side identity linkage disadvantage, and flags 'Read-only.' This level of candor about a privacy trade-off is exactly the kind of behavioral information an agent needs before making a call, and it goes beyond the schema and annotations.

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 somewhat long for a read-balance tool, but it front-loads the core purpose and then delivers essential context. The trade-off explanation about relay linkage is a hard requirement for safe use and justifies the extra length; it is not padded but each part of the text earns its place. The structure keeps the essential information at the beginning and places the cautionary details after.

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 tool is simple (one address parameter, no output schema) and the description covers the input, the privacy behavior, the trade-off, and the supported chains. The only missing piece is explicit return format (e.g., units or structure of the balance), but for a basic read-balance action, this is a minor anchorable gap; the description still enables effective calling for most scenarios.

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 defines the only parameter (address) with a description that states '0x address (e.g. a derived stealth address)'. Because schema coverage is 100%, and the description adds nothing beyond the schema (it does mention 'derived stealth' but that is already present in the schema), the baseline score of 3 is appropriate here.

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 begins with a specific verb and resource: 'Reads an address balance through the NULL server-side RPC proxy,' and further scopes this with the read-only nature and supported chains (Base + Arbitrum). This is more concrete than many MCP definitions; even without naming a sibling, it clearly communicates the unique role of the tool among the null_* utilities.

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 does not explicitly name an alternative, but it offers clear context-driven usage advice: it explains the privacy rationale, warns against the linkage risk, and recommends batching addresses to mitigate that risk. This helps an agent decide when the tool is appropriate, though it stops short of describing when not to use it or naming a competing tool.

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