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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses that nothing is broadcast, that the server cannot reach Sui's execute RPC at all, that no signature is accepted, and precisely which fields the report contains. This is the kind of safety and behavior detail an agent needs before calling a transaction-simulation tool.

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 and the result payload, then the input contract, then the no-broadcast guarantee. Every sentence carries information, though the middle sentence is dense with a long enumeration of reported fields that could be trimmed slightly.

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?

There is no output schema, so the description must carry the return-value burden — and it does, itemizing abort location, gas, created/mutated/deleted objects, per-address balance changes, decoded command return values, and emitted events. Combined with the input contract and safety notes, nothing essential is missing.

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?

Only one parameter and schema coverage is 100%, so the schema already documents the base64 BCS TransactionData format, pattern and length bounds (baseline 3). The description adds non-schema meaning — that it is the exact argument sui_dryRunTransactionBlock takes and that no signature is required or accepted — which nudges it above baseline.

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?

Opens with a specific verb+resource ('Run a transaction against current state') and enumerates exactly what it reports: success/abort, gas, object mutations, balance deltas, return values, events. It also names a sibling (expandResult) and an equivalent (sui_dryRunTransactionBlock), so an agent can place it precisely among the other Sui 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?

Clearly states the operating context: it takes the same base64 BCS TransactionData a wallet/SDK produces, accepts no signature, and never broadcasts. It names expandResult as the alternative for raw/unshaped output. It lacks an explicit 'when not to use this vs suiGetObjects/rpcCall' statement, but the context is unambiguous.

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