preview_steps

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial context beyond them: sequential state dependency between steps ('an approval before a mint works'), the per-step and net returns, and the caveat that on-chain state can change before landing. This is rich behavioral disclosure.

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?

Three front-loaded sentences: purpose first, mechanics and return shape second, provenance and caveat third. Every sentence earns its place with no redundancy.

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?

Complete for a simulation tool. Although an output schema exists (so return values need not be restated), the description still clarifies the return shape and sequencing semantics, and covers the state-may-change caveat an agent needs to interpret results 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?

Schema coverage is 100%, so the schema already documents from, steps, and the target/calldata aliases and optional value/gas. The description adds provenance meaning by telling the agent to pass steps 'exactly as' the producing tools return them and emphasizes they are applied in order, which goes modestly beyond the schema.

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?

States a specific verb+resource with precise scope: 'Simulate a list of transactions in sequence against the latest Base block ... before anything is signed.' This clearly distinguishes it from siblings like prepare_action (which produces steps) and the read-only state tools.

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?

Explicitly frames when to use it ('before anything is signed'), and names the exact sibling tools whose output feeds it (prepare_action, invest_usdc_to_gblin, swap_gblin_to_usdc_jit). It also warns that a successful preview is 'evidence, not a guarantee,' which sets correct expectations about when the result is authoritative.

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