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

With no annotations, the description carries the full burden, and it delivers: it states the simulation runs on mainnet, never sends, costs $0.01 per call, and returns specific diagnostics. This openly discloses the side-effect-free nature and the pricing, leaving little ambiguity.

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?

Every sentence earns its place: purpose, output contents, usage trigger, no-send guarantee, cost, and parameter format. The most decision-relevant information is front-loaded, making the description efficient and easy to parse.

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?

Even though there is no output schema and no annotations, the description lists expected return values, explains the input format, and states the cost. For a single-parameter simulation tool, this is complete enough for an agent to call it 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 description coverage is 0%, but the description adds crucial encoding details—'base64-encoded signed or unsigned Solana transaction'—telling the agent exactly what to pass. This fully compensates for the bare schema, which only labels the field as 'Transaction Base64'.

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 the intended outcome ('Find out whether your transaction will succeed') and precisely names the operation: simulate on mainnet, returning decoded errors, logs, compute units, and expected account changes. 'Never sends — simulation only' clearly distinguishes it from any actual submission tool among the siblings.

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?

It provides an explicit trigger: 'Use before submitting any unfamiliar or high-value transaction,' and clarifies that it only simulates, never sends. It doesn't name specific alternative sibling tools or state when not to use it, but the guidance is still clear and actionable.

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