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

Beyond the readOnlyHint annotation, the description discloses that state-changing functions are rejected, that historical queries are supported, and that calls use a bounded RPC timeout and rate-limit retry policy. This adds meaningful behavioral context about safety and reliability that is not available from annotations alone.

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 concise at five sentences, front-loaded with the core purpose. Each sentence adds value, covering safety, historical queries, caller context, and RPC policy. It is slightly longer than necessary but remains efficient and well-structured.

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 complexity (8 parameters, output schema, readOnlyHint), the description covers key functional aspects: arbitrary view/pure calls, ABI requirements, rejection of state-changing functions, historical block support, caller context, and timeout/retry behavior. It does not explain return formatting, but the output schema covers this, and not all parameter semantics are repeated, which is acceptable.

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 descriptions cover 100% of parameters, so the description adds little extra information. It mentions providing the ABI fragment and block_identifier, but these are already well-documented in the schema. The description does not clarify ambiguous parameters like args vs args_json, so it remains at the baseline for high 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 calls any view/pure function on a smart contract and returns the result. It specifically distinguishes itself by noting state-changing functions are rejected, making it distinct from sibling tools that perform specific reads or transactions.

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 provides clear context by stating it is for view/pure functions, explicitly excluding state-changing functions for safety. It also mentions support for historical queries and caller_address, which guides when to use these features. However, it does not explicitly mention when to prefer sibling tools like get_erc20_balance for specific token reads.

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