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

With no annotations, the description carries the full burden of behavioral transparency. It discloses that the tool is non-custodial, returns a plan of unsigned swaps, includes only gas-positive legs, rides the sweep fee on one leg, and requires the user to approve each leg's approvalTarget and sign. This goes well beyond the schema and gives the agent an accurate model of what happens before, during, and after the call.

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 four compact sentences with no filler. The first sentence front-loads the core purpose, followed by input handling, output plan characteristics, and supported chains. Every sentence contributes essential information without redundancy.

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?

This tool has no output schema and no annotations, so the description must provide sufficient context for correct invocation. It explains the plan output, the signing/approval flow, and supported chains. It does not detail the exact structure of the returned plan or edge cases (e.g., what happens when no gas-positive legs exist), but the description gives the agent enough to call the tool and understand the result at a high level. Minor gaps prevent a 5.

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 description coverage is 100%, so the baseline is 3. The description adds minimal semantic value: it reiterates the default USDC, the dust list shape, and that the caller knows their own balances. These points are already present in the schema, so the description does not meaningfully enhance parameter understanding beyond what structured data provides.

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 states a specific action—'Consolidate many small leftover token balances (dust) into one token (default USDC) on an EVM chain'—with a clear verb and resource. It is distinct from sibling tools like get_swap_quote or build_swap_transaction, which handle general swaps, while this tool is specifically for sweeping dust balances.

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?

The description clearly implies when to use this tool: when you have multiple small leftover token balances to consolidate into one token. It does not explicitly exclude use cases or reference alternatives, but it provides enough context (e.g., 'you know your own balances', supported chains) for an agent to recognize the intended scenario. There are no explicit exclusions, but the usage context is clear.

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