simulate_transaction

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

No annotations, so the description carries the full burden - and it discloses rich behavior: the exact guard set checked, the spend policy, that the gas estimate fails on revert, worst-case fee, balance coverage, and the significant local-vs-hosted mode difference. It omits any permission/auth requirements or rate limits, but for a read-only simulation this is close to complete.

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?

Front-loaded with the core action, then a dense enumeration of what it verifies, closing with the mode distinction. The first sentence is a long list but every clause earns its place; only the run-on length keeps it from a 5.

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?

With no output schema and no annotations, the description steps up to describe the returned checks (gas estimate, worst-case fee, balance coverage, return data) so an agent knows what comes back. It does not describe failure/error shape or how to interpret a failing guard, leaving 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 coverage is 100%, so the schema already documents every parameter (including that wallet_id is ignored in local mode). The description adds contextual framing (cap checks, spend policy) but no syntax or format detail beyond the schema, so the 3 baseline applies.

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 ('Dry-run/simulate') and resource (EVM transaction) and sharpens the distinction from sign/send siblings with 'with nothing signed'. An agent can immediately tell this is a non-mutating preflight.

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?

'Dry-run ... with nothing signed' clearly establishes the preflight context, and the local-vs-hosted mode note signals when each path applies. It stops short of naming alternatives (e.g. send_transaction) or stating the ordering ('call before sending'), so no explicit when-not guidance.

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