token_wallets

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

Read-only and non-destructive are already declared in annotations, and the description adds independently useful behavior: per-class list cap at 100 and real counts in *_total fields. It also conveys the output granularity, which goes beyond what annotations already provide.

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 dense sentences with no filler. The cost is front-loaded, core output classes come second, the cap behavior third, and the sibling distinction closes it. Every sentence earns its place.

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 one required parameter fully covered, an output schema present, and the description explaining the key truncation caveat and the difference from inspect_token, nothing needed to invoke the tool correctly is missing.

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?

The only parameter, mint, is fully documented in the schema as a Solana token mint in base58, so high schema coverage sets a baseline of 3. The description adds little parameter-level detail but does clarify that the mint identifies a single token for wallet analysis.

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 exactly what is returned: named wallet addresses behind a token, grouped by behavioral classes (insiders, snipers, early buyers, etc.), with funder, link count, and cluster. It also explicitly differentiates itself from inspect_token by noting that this tool provides addresses rather than counts.

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 final sentence explicitly contrasts with inspect_token ('inspect_token gives counts, this gives addresses'), which tells an agent when this tool is the right choice. It stops short of broader when/when-not guidance against the many other sibling tools, but for address-level wallet data the guidance is adequate.

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