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

With only readOnlyHint=true supplied, the description carries most of the burden and does add real context: the position NFT is retained, fees/rewards are swept into the same operation, liquidity is bounded by decoded current state, and the whole batch is all-or-nothing ('require every inner call to succeed'). It does not say what the prepared output looks like or whether approval steps are needed, but the output schema covers the return shape.

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, front-loaded with the operation and its scope, then preconditions, then output handoff. Dense but every sentence carries a constraint. Mild deduction for jargon like 'current_state_query' and 'inner call' that assume familiarity with sibling tooling.

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 multi-position batch preparation tool with a 3-parameter schema and an output schema, the description covers scope, safety constraints, and recipient/earnings handling adequately. The remaining gap is that it never states whether approvals are included or how the batch behaves on partial failure beyond 'require every inner call to succeed'.

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%, so the baseline would be 3, but the description adds meaning beyond the schema: it explains that liquidity must not exceed the decoded current-state value, that owner must match expected_owner (the sender constraint), and that the recipient receives principal plus earnings estimates. These are semantic constraints rather than restatements of the field descriptions.

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 gives a specific verb (Prepare) plus the exact resource (partial or full withdrawals from one or more owned positions in one plan) and states the two distinguishing behaviors: fees/Ve33 rewards are collected and the NFTs are kept. That separates it cleanly from siblings like prepare_lp_position_deposit, prepare_lp_position_earnings_claim, and prepare_uniswap_v3_remove_liquidity without needing 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?

It gives concrete preconditions — read each position's current_state_query first, never request more liquidity than that decodes, require every inner call to succeed, and require owner to equal expected_owner. What is missing is explicit routing against alternatives: it never says when to use this instead of a plain remove-liquidity tool or a separate earnings-claim tool when only rewards are wanted.

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