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

Adds real behavior beyond the annotations: data is read live 'from the chain now', it performs a gas-vs-fees comparison, and — most importantly — with no arguments it defaults to the agent's own wallet, whose full address is disclosed. 'Reads only, signs nothing' restates readOnlyHint but does no harm. Missing only edge behavior such as what happens for an unknown position id.

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 and dense: the scope, then the returned facts, then input options, then a safety close. A few flourishes ('the free half', 'whether collecting them pays for the gas') cost length but carry information. Nothing is genuinely wasted, though the single run-on sentence across em dashes is harder to scan than it needs to be.

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?

With no output schema, the description takes on the return-value burden and does it well: it enumerates range status, edge headroom, holdings, BNB valuation, owed fees and gas viability. Safety and default-input behavior are covered. The only gap is failure modes — what an empty or unresolved position returns.

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 is 3: the parameter descriptions already define position, wallet and address, including the wallet/address aliasing, and the description repeats the id-or-wallet choice rather than extending it. It does add the valuable default case (no id and no wallet means the agent's own position at a stated address), which is the one piece of meaning not in the schema.

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?

Specific verb and resource: 'look at a PancakeSwap V3 liquidity position on BNB Chain, read from the chain now', followed by exactly what is reported (range status, room to each edge, holdings, BNB value, fees owed, gas breakeven). The opening phrase 'Rebalancing, the free half' implicitly frames it against the sibling lp_position_plan, but it never names that sibling, so differentiation is inferred rather than stated.

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?

Usage context is present but only implied — 'the free half' of rebalancing suggests a read-only inspection step ahead of a plan, yet there is no explicit 'use this when X, use lp_position_plan when Y'. The input-selection guidance ('give a position id or a wallet that holds one') is useful but is really parameter behavior rather than when-to-use guidance.

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