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

Annotations already cover readOnly/openWorld/non-destructive, and the description adds genuinely non-obvious behavioral context: the call is paid (0.10 USD1, half in $BOBAI, or free with 1,000,000 $BOBAI held), payment is over x402 via signature with no transaction, and an ERC-8183 escrow alternative exists. It also states explicitly that it signs nothing on the user's position, which is meaningful safety detail beyond the annotations. The only gap is that it never clarifies what happens on unpaid or failed payment.

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?

Two enormous run-on sentences with three levels of nested parentheses, and payment/legal terms are front-loaded before the tool's actual function. The substantive content is relevant but the structure forces the reader to untangle pricing, x402 mechanics, and analytical scope in a single pass. Sizing is excessive for what amounts to one analytical capability.

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 does explain the analytical dimensions returned (range, edge room, BNB value, fee/gas economics, chosen width and its backtest rationale, spare BNB impact) and states 'Calling this tool returns the terms.' What it omits is the shape of that answer and any error/empty-position handling, so an agent knows what is computed but not what it will receive.

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% and the single 'task' parameter is documented as 'What you want, with the address in it.' The description implies an address-bearing request ('about yours') and enumerates what the agent will evaluate, but adds no syntax, format, or routing guidance for the task string itself. Baseline 3 is appropriate when the schema carries the parameter definition.

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 eventually conveys that this tool analyzes a PancakeSwap V3 LP position and decides on rebalancing: range status, edge room, holdings in BNB, fee vs. gas, re-set width, and spare BNB deployment. However, the core purpose is buried mid-sentence behind payment terms, and there is no explicit differentiation from the sibling lp_position_look beyond the word 'plan'. An agent can infer the purpose but must parse past pricing boilerplate to find it.

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?

There is no statement of when to call this versus lp_position_look, nor any prerequisites or exclusions. The only usage-adjacent line is 'It reads and plans; it signs nothing on your position,' which describes behavior rather than selection criteria. The word 'plan' versus 'look' implies a distinction the description never makes explicit.

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