evm_trace_call_revert_debugger

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

With no annotations, the description has to disclose behavior itself. It does: it is a parsing-only operation with no mutation, and the cost note '(0.045 USDC on Base L2)' alerts the agent to payment implications. However, it does not say whether the operation is local vs network-backed, what happens if no valid paymentSignature is provided, or how failures are surfaced, so the burden is only partially met.

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 single sentence front-loads the core behavior and concrete outputs, and the parenthetical fee is the only extra detail. There is no boilerplate or redundancy, so every token earns its place.

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?

For a tool with no output schema and only a generic payload parameter, the description lists the returned diagnostic fields (depth, opcode, sub-contract, revert message) and names the input domain, which is reasonably complete. It is weakened by leaving payload formatting unspecified and by stating a fee while the input schema marks paymentSignature optional, so an agent may not know whether payment is mandatory.

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 coverage is 100% but the payload description is generic ('Input parameters or JSON string payload'). The tool description adds that the payload should be a debug_traceTransaction call tree, which helps, but it never explains the expected shape of that tree or how the optional paymentSignature interacts with the stated cost. This meets the baseline without adding strong parameter-level value.

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 opens with a specific verb ('Parses') and a specific resource ('Geth/Nethermind debug_traceTransaction call trees'), then names the exact outputs (depth, instruction opcode, sub-contract, revert message). This is enough to distinguish it from siblings like decode_revert_reason_hex, which only decodes a revert hex string, without needing to open the schema.

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 context for use is clear: when the agent has failed debug_traceTransaction call trees and needs to locate the exact failing depth, opcode, sub-contract, or revert message. It does not name alternatives or exclusions, so it falls just short of 5, but the domain is specific enough that misuse with unrelated EVM tools is unlikely.

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