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

Annotations already cover read-only, idempotent, open-world and non-destructive, and the description adds real behavioral context on top: live chain head semantics, the block number returned for reproducibility, and a $0.01 cost that affects invocation decisions. It does not cover failure modes (bad address, unsupported token, RPC error) or whether the cost is incurred on failure.

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 sentences, each earning its place: capability and chain scope first, return shape second, scope limits and price last. No filler or repetition of the title.

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 carries return-value disclosure and does so adequately (native balance, ERC-20 balances, metadata, block number). The remaining gap is call-behavior detail — default chain resolution and what happens when a requested token or the wallet itself is invalid — for a modest three-parameter read tool.

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 description coverage is 33%, so the description must compensate and does only partly: it names the six chains and ties 'requested ERC-20 balances' to the tokens array. It never states that chain defaults to base, nor clarifies that omitting tokens yields native balance only, leaving the undocumented wallet and chain parameters thin.

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 (read) and resource (a wallet on six named chains) at the live chain head, then enumerates exactly what comes back. Whether it overlaps the sibling get_token_snapshot is disambiguated implicitly by the wallet-vs-token scope, so an agent can pick correctly.

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 'this is a point-in-time read, not custody, valuation, proof of reserves or transaction authorization' clause gives concrete when-not-to-use boundaries that no sibling covers. It stops short of naming an alternative tool for those other needs, so it is a strong 4 rather than a 5.

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