evm_multicall

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

With readOnlyHint and openWorldHint annotations already present, the description adds minimal behavioral context. It mentions 'multicall RPC request' but does not disclose failure handling behavior or return format, which could be relevant given the allowFailure parameter.

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 a single concise sentence, front-loaded with the primary purpose, and contains no redundant words. Every word contributes to understanding the tool's function.

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 schema fully documents parameters and annotations cover read-only safety, the description is largely sufficient for a simple batch read tool. However, the lack of output schema and absence of return format in the description is a minor gap.

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 all parameters are adequately documented in the schema. The description itself repeats no parameter details, but the baseline is 3 due to full schema coverage.

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 batches multiple contract read calls into a single multicall RPC request, using a specific verb and resource. It distinguishes itself from single-call tools like evm_read_contract and write tools like evm_write_contract.

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 when multiple contract reads need to be batched, and clearly indicates it is for read calls only, excluding write operations. However, it does not explicitly name alternatives or state when not to use it.

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