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

Adds real context beyond the annotations: it explicitly says it does not sign, submit, or broadcast and does not accept a private key, which matters a lot given destructiveHint=true and readOnlyHint=false on a 'withdraw' tool. It also pins the single endpoint. It stops short of describing auth requirements, rate limits, or what the unsigned transaction contains — but with full annotations the bar is lower.

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 action and the endpoint constraint, followed by the non-signing caveat and then context. Slight redundancy: 'Withdraw MEV' and 'Solana API endpoint for withdrawing MEV rewards on Solana' repeat the same fact and the 'on Solana' phrase is duplicated, but overall it is tight and every sentence mostly 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?

An output schema exists, so return-value explanation is unnecessary, and the rich annotations cover the safety profile. The description fills the remaining critical gap (unsigned, no private key, single endpoint) for a one-parameter nested-body tool. It could still mention whether the built transaction must be signed within a validity window or what the caller must do next, but it is reasonably 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 description coverage is 100% and the nested body fields (mevFee, gasless, vybeSOL, stakeAccountAddresses, simulate, partner, router) are all documented in the schema, including the auto-fetch behavior when stakeAccountAddresses is omitted. The description adds no parameter-level meaning of its own, so baseline 3 applies.

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 ('Withdraw MEV', 'claim accumulated MEV rewards from staking positions like Jito') and names the exact endpoint POST /v4/wallets/util/withdraw-mev. It also clarifies the output artifact (an unsigned transaction), so an agent knows what it gets. It does not explicitly contrast itself with the sibling builders (build-swap, build-close-token-accounts), which keeps it at 4 rather than 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 implies usage ('Build a transaction to claim accumulated MEV rewards') and gives one hard constraint ('Calls only POST /v4/wallets/util/withdraw-mev'), but never says when to prefer this over the other build-* tools or what prerequisites exist (e.g., must have staking positions with MEV rewards). Usage is inferable but not spelled out.

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