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

Annotations already declare readOnlyHint=true, and the description reinforces the read-only nature. Beyond annotations, it discloses return format (success status and raw return data per call) and failure behavior (allowFailure prevents one failed call from aborting the batch). This adds valuable behavioral context that annotations do not cover, with no contradictions.

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 tight and well-structured: three sentences each carrying essential information—purpose and contract address, return format, and failure-handling tip. No fluff or redundancy, and the most critical information 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?

Given the tool's simplicity (one parameter, no output schema), the description is exceptionally complete. It covers the purpose, network specificity, return behavior, and failure semantics. The absence of an output schema is compensated by explicitly stating what the tool returns. No gaps for an agent to invoke it correctly.

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 schema fully documents the 'calls' array and its sub-fields (target, callData, allowFailure). The description adds meaning by explaining how allowFailure affects batch execution, which is not fully captured by the schema's field description. It also contextualizes the overall behavior of the batch operation. This goes beyond the schema baseline.

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 clearly states the tool's purpose: batch multiple read-only contract calls into a single RPC round trip using Multicall3 on Ethereum mainnet. It specifies the verb (batch), resource (contract calls), and mechanism (Multicall3 contract address), distinguishing it from single-call tools like eth_call and chain-specific variants like mezo_multicall.

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 context: use this when you need to batch multiple read-only calls for efficiency. It also offers specific guidance on allowFailure. However, it does not explicitly name alternatives or state when NOT to use it (e.g., for a single call or for state-changing calls). This is clear context without explicit exclusions.

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