defi-agent

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantive context beyond them — 'reads only, signs nothing', a live on-chain read, and the default-target wallet address. It also enumerates what the read produces, so behavioral expectations are well set.

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 information-dense, with the core action stated first and no wasted sentences. It is somewhat ornate ('Rebalancing, the free half') and packs everything into two very long clauses, but every clause carries operational content.

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 carries the return-value burden and does so — it lists in-range status, room to each edge, holdings, BNB value, fees owed, and gas economics. Combined with the read-only scope and input fallback, an agent has what it needs to call and interpret this tool.

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 description adds meaning beyond the schema by disclosing the fallback behavior (no id/wallet → reads the agent's own position) and clarifying the dual 'wallet'/'address' input path, which the schema alone does not convey.

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 names a specific verb and resource — 'look at a PancakeSwap V3 liquidity position on BNB Chain' — and scopes it as a read ('read from the chain now', 'Reads only, signs nothing'). The phrase 'the free half' gestures at the sibling lp_position_plan without ever naming it, so sibling differentiation is implied rather than explicit.

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 invocation conditions: 'Give a position id or a wallet that holds one; with neither, it reads the position this agent runs itself' and even supplies the fallback address. That is clear when-to-use guidance for each input path, but there is no explicit when-not-to-use or named alternative to route to.

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

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

The annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered; the description adds genuinely new behavioral facts: it signs nothing on the position, it only reads and plans, and the answer is a paid artifact sold over x402 at a specific URL (0.10 USD1 or half in $BOBAI) or via ERC-8183 escrow. That payment/billing requirement is exactly the kind of context annotations cannot express. It stops short of describing latency, failure modes, or the shape of the delivered answer.

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?

The description is one sprawling run-on sentence dense with em-dashes and nested parentheticals, so the core purpose is not front-loaded and key facts (payment, read-only) are buried. Nothing is wasted per se, but the structure actively impedes scanning of what should be a short statement of what the tool computes and what it costs.

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 an open-world paid tool with no output schema and a trivial one-param schema, the description does cover the computational scope and the payment mechanism. What it omits is the actual invocation/return workflow — 'Calling this tool returns the terms' is vague about whether the caller gets a payment challenge or the answer, which matters for an x402-gated service. Adequate but with a real gap around how the call resolves.

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?

With a single parameter and 100% schema description coverage ('What you want, with the address in it'), the schema already carries the meaning, so the baseline is 3. The description adds nothing about the task string itself — no format, no required address syntax, no examples of what 'what you want' should contain.

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 names a specific verb and resource: it computes what the project's PancakeSwap V3 agent 'would decide about yours', spelling out the concrete outputs (in-range status, room to each edge, holdings/value in BNB, fees owed vs. gas, re-set decision and width). That is far more than a restatement of the name. However it never distinguishes this from the sibling lp_position_look, so an agent must infer the boundary from the incidental phrase 'the paid half'.

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 is only implied: the opening 'the paid half' suggests a free counterpart (presumably lp_position_look) without ever naming it or stating the condition for choosing this tool over that one. There are no exclusions or prerequisites beyond the incidental note that it 'reads and plans; it signs nothing on your position'. An agent can guess when to reach for this, but it is left to inference.

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