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

Annotations already cover read-only, idempotent, open-world, and non-destructive hints. The description goes far beyond by disclosing return structure (native and per-token fields), error handling (ok:false for non-ERC-20, 5xx not charged), security warnings (attacker-controlled token symbols, untrusted data), performance (0.3–2 s), pricing, and free-tier rate limits. This is rich behavioral context.

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 front-loaded with the core purpose, then logically flows through inputs, outputs, error behavior, performance, pricing, and security. Every sentence adds actionable information for an agent, with no wasted words despite its length.

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?

There is no output schema, so the description must explain return values—it does so thoroughly, including field names and error semantics. It also covers edge cases, security, rate limits, and timing. Combined with annotations that carry the safety profile, nothing an agent needs to invoke correctly is missing.

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 100%, so the schema already documents all three parameters in detail. The description repeats the input details (chain enum, address format, optional tokens up to 20) but adds no new semantic meaning for the parameters themselves. Baseline 3 is appropriate.

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: 'read the native balance and up to 20 ERC-20 balances of an address on Ethereum or Base in one call.' It clearly distinguishes itself from sibling tools like get_balance or get_token_info by emphasizing multi-token retrieval in a single call. An agent can immediately understand the tool's function.

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 implies usage—you call it when you need native and multiple ERC-20 balances for an address—but never explicitly states when to choose this over alternatives such as get_balance (for a single native balance) or get_token_info. No exclusions or sibling comparisons are provided.

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