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

Annotations already declare readOnly=false, destructive=true, idempotent=false, and openWorld=true. The description usefully adds that it does not sign or send and that it should not be automatically retried after expiry, but it does not explain what is destructively modified or what the preparation produces.

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 compact sentences with no filler, covering the prerequisite, next step, and prohibitions. The key 'does not sign or send' clarification appears after imperative instructions but still earns its place.

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?

For a mutation tool in a manual signing workflow, the description covers the prerequisite, next step, and expiry behavior adequately. However, with no output schema and a destructive annotation, it never says what 'prepare' returns or what state it changes, leaving the agent to guess the result.

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?

The single handoffId parameter has 0% schema description coverage. The phrase 'for this handoff' loosely connects the parameter to a handoff identifier, but it does not explain where to get it, that it is required, or that it uses a 64-character hex format, so the description does not compensate for the schema gap.

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?

It names the action (prepare) and object (immutable transaction) scoped to a handoff, and clarifies that it does not sign or send, which distinguishes it from submit_wallet_payment. It does not explicitly name the sibling that handles sending, which keeps it from a 5.

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 gives a clear prerequisite (owner connected Phantom) and next step (ask owner to review and sign on the existing owner page), plus an expiry-related exclusion. It never names an alternative tool for the actual send, so the when-to-use guidance is strong but not fully explicit.

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