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

Annotations already declare read-only, non-destructive, closed-world, so the bar is lower, yet the description still adds real behavioral context: the read is pinned to one block, prices come from OrbitWan's table, amounts are base-unit strings, and the total is nulled with a failed count when any per-token read fails. That partial-failure semantics is exactly the kind of detail annotations cannot carry.

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?

Three short sentences, each carrying distinct information: what is returned, how amounts and prices are derived, and how failures are surfaced. No filler and the core identity is front-loaded.

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?

With no output schema, the description takes on return-value explanation and does reasonably well (base-unit string amounts, priced values, null total plus failure count). The shape of the per-token list itself and address format expectations are the remaining minor gaps.

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 0% for the single required 'address' parameter, so the description must compensate. It only implies the parameter ('of an address') without specifying expected format (hex, checksummed, chain prefix), so it partially but not fully closes the gap.

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 resource (token balances of an address) with a clear verb (read live at one pinned block), which separates it from siblings like get_address_activity or get_address_flows. It does not explicitly name which sibling to use for non-balance questions, but the resource is unambiguous.

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?

There is no when-to-use/when-not guidance and no mention of alternatives (e.g., get_token_prices for price-only queries, list_tokens for token metadata). The description describes what the tool returns rather than when to select it over the many adjacent get_address_* siblings.

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