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

The description reads as an executed state change ('Remove liquidity and take principal plus fees to the sender'), while annotations declare readOnlyHint=true. That is reconcilable only if the reader assumes the 'prepare_' prefix means it merely builds an unsigned transaction for signing, and the description never states that. It also omits allowance/approval requirements and any warning that the resulting transaction is irreversible once broadcast.

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 dense sentences with no filler, front-loaded on the primary effect and immediately followed by the optional burn branch. The phrasing is jargon-heavy ('minima applied to the full position') but each clause carries information an agent needs.

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 12-required-parameter financial transaction with no annotations beyond a read-only hint and no output explanation needed, the description leaves two critical things unstated: whether it returns calldata for signing rather than executing, and whether prior approvals are required. Given the value at stake these gaps are material, not cosmetic.

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?

Real meaning is added beyond the schema: burn coupling to liquidity:0, minima applied to the full position when burning, the requirement for exact pool currencies and hook data, and that amount0_min/amount1_min are uint128 bounds on principal. With 15 parameters and only 73% schema coverage, however, fee/tick_spacing ordering, deadline semantics, and hook_data usage in the non-burn path remain unexplained.

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 first sentence names a specific verb and resource ('Remove liquidity', principal plus fees to the sender) and the second sentence describes the V4-specific burn path. V4 specifics (pool_id, hooks/hook_data, NFT burn) separate it from prepare_uniswap_v3_remove_liquidity, though the text itself never names the siblings it is distinct from.

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?

Useful conditional guidance is given for the burn path ('burn:true requires liquidity:0 and withdraws the entire NFT'), which is a real when-to-use rule. What is missing is routing guidance: no statement of when to choose this over prepare_uniswap_v4_collect_fees, prepare_uniswap_v3_remove_liquidity, or prepare_lp_position_withdraw, and no prerequisite note about token approvals.

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