Prepare a guarded SOL transfer

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

With no annotations, the description fully discloses behavior: the three-step process (policy check, simulation, staging), the conditionality (only if both pass), and the note that nothing is signed or sent. This addresses common concerns about safety and side-effects.

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 sentences, each providing essential information: the action, the return value, and the key disclaimer. No redundant details, and the purpose is front-loaded.

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?

The description includes the return type (actionId), clarifies the output usage (for execute_action), and explains the conditional staging. It does not explicitly detail failure cases but implies them. For a tool with three required params and no output schema, this is nearly complete.

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% with descriptions for each parameter. The tool description adds contextual workflow but does not significantly enhance understanding beyond what the schema provides. Thus, baseline 3 is appropriate.

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 clearly states that the tool checks safety policy, simulates, and stages an unsigned transaction, returning an actionId for execute_action. It distinguishes from siblings by specifying the multi-step guarded process.

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 description implies when to use (as a preliminary step before execution) and mentions the returned actionId for execute_action. However, it does not explicitly state when not to use or provide alternative tools for different scenarios.

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