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

Annotations already declare readOnly and openWorld; the description goes further by disclosing free/keyless access, USD pricing via DefiLlama, and that spam and dust are filtered out — filtering behavior an agent would otherwise misread as an empty wallet. It also instructs rendering the `display` markdown, which is behavior not encoded anywhere else. Loses a point only because chain-coverage edge cases (partial failures, empty results) aren't addressed.

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 with the core purpose and scoped per chain, then output shape, then orchestration hints — a sensible ordering. It is dense to the point of being slightly run-on (the playbook workflow list is a long tail), but nearly every clause carries actionable information.

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 compensates by naming the return fields (totalUsd, per-chain totals, holdings, suggestions, swapUrl, `display` markdown) and what the suggestions mean. An agent can call this and act on the result without opening any other tool definition.

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 baseline is 3, but the description adds real semantics beyond the schema: the `chains` param narrows EVM chains only ('default all of the address's VM'), and ENS/SNS names are accepted only after resolve_name — a constraint that contradicts the schema's plain address string and would otherwise cause a failed call.

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?

States a concrete verb+resource+scope: a multi-chain portfolio read for any address, enumerating exactly which assets are covered per VM (EVM native + SwapChan-listed tokens, SOL + SPL/Token-2022, BTC, TRX + TRC-20). It is clearly distinguishable from siblings like wallet_pnl or find_money because it is a holdings snapshot rather than P&L or discovery.

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?

Gives explicit upstream conditions ('Accepts ENS/SNS names too if you resolve_name first') and an explicit next step ('offer the user a SwapChan swap (get_quote / the swapUrl)'), plus routes complex workflows to swapchan_playbook. An agent knows both prerequisites and follow-on actions without inference.

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