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

Goes well beyond the annotations by disclosing the internal validation pipeline: HMAC permit verification, signature verification, expiry checking, and re-simulation before broadcast. Those are exactly the failure modes an agent needs to anticipate, and they add real information the destructive/openWorld hints do not convey.

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?

Four short sentences, front-loaded with the action, then prerequisites, then the conditional parameter case, then the impact flag. No filler and each sentence introduces a distinct decision the caller must make.

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 destructive, open-world, non-idempotent mutation with six params and no output schema, the description covers the preconditions, the conditional argument, and the validation steps. It does not say what a successful submission returns (transaction hash, status) or how failures surface, which leaves a small gap for a high-impact operation.

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?

With 0% schema description coverage the description must carry the load, and it does for most params: permit and summary must be passed unchanged from prepare_withdraw, unsignedTransaction is conditionally required, and confirmHighImpact maps to high-impact operations. wallet and signedTransaction are only implied by the opening sentence, and the nested summary object's contents are never characterized.

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 and resource ('Submit a wallet signed withdrawal') and immediately distinguishes the action from the sibling prep step by requiring artifacts 'from prepare_withdraw'. An agent can identify this as the broadcast/finalization step of a two-phase withdraw flow without opening the schema.

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?

Gives a clear workflow prerequisite (obtain summary and permit from prepare_withdraw) and a conditional rule for when to include unsignedTransaction (wallet-appended instructions such as Phantom Lighthouse) plus the confirmHighImpact requirement. It stops short of naming when NOT to use it versus other submit_* siblings, but the guidance is actionable.

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