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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description nonetheless adds real behavioral context beyond them: the existence of archived (soft-deleted) wallets that should be skipped, and the fact that returned addresses are reused by ask_anon and portfolio_*. It stops short of stating permissions or matching fuzziness.

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?

Three sentences, front-loaded with the resource and returned fields, then usage, then cross-tool linkage. Every clause carries an actionable constraint (one-per-type cap, skip archived) with no filler.

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 a no-parameter, no-output-schema read tool the description is nearly self-sufficient: output fields, selection rules and downstream consumers are all covered. Only minor gaps remain, such as whether an empty wallet list is possible or how matches behave when a name is ambiguous.

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?

Zero parameters, so the baseline is 4 per the rubric. The description compensates usefully by clarifying the shape of the returned records (type values such as evm, solana, ton) rather than leaving the fields unnamed.

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 specific verb (List) plus resource (user wallets in Hey Anon) and enumerates exactly what each entry contains: display name, type, address, labels, archived flag. Nothing about it could be confused with siblings like address_book_list or portfolio_*.

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 when-to-use (call before ask_anon to pick addresses), the selection rule (at most one per type), the matching heuristic (display name, label or address) and an exclusion (skip archived wallets). It also routes the agent to the related portfolio_* tools, so alternatives are named rather than implied.

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