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

With no annotations, the description carries the full behavioral burden. It does disclose genuinely useful behavior beyond the schema: the Alchemy backend, the $0.004 USDC per-address cost model, and the 1-20 batch size. It omits read-only confirmation, any auth/permission requirement, rate limits, partial-failure behavior when some addresses are invalid, and return shape, leaving meaningful gaps.

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?

Two tight sentences, zero filler. The core capability is front-loaded and the cost/size constraints follow immediately, so an agent can extract the essentials at a glance.

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 simple two-parameter read tool with no output schema, the description covers purpose, provider, cost, and bounds, which is close to sufficient. The remaining gap is that it does not describe the return payload despite no output schema existing, and chain behavior/default is left entirely to the schema.

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 50%: the chain parameter is documented in the schema with its enum-like value list, while addresses has no schema description. The description compensates partially by clarifying that addresses are ERC-20 balance lookups batched together and priced individually, which adds meaning beyond the raw array type. It says nothing about the chain parameter, so it does not fully offset the coverage 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?

The description states a specific verb and resource ('Batch ERC-20 balances for many addresses in one call') and names the data provider (Alchemy). The 'many addresses in one call' phrasing implicitly separates it from the single-address sibling cortex_token_balances, but it never names that sibling, so the differentiation is inferential rather than explicit.

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 conveys the usage context (multi-address batching) and the 1-20 address envelope, plus per-lookup pricing that an agent could weigh in a cost/volume decision. However, it gives no explicit when-not guidance and never routes the agent to cortex_token_balances for a single address or to cortex_aggregate_prices for valuation.

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