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

Annotations only cover read-only and open-world, so the description carries the real burden and does: spam-like airdrops are hidden and counted, unsellable tokens are listed apart, and stale prices are capped at 15 minutes and flagged via priceAsOf. It also discloses valuation sources per asset class, which the agent would otherwise have to guess.

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 purpose and scope before the valuation detail, and every clause carries information (pricing sources, risk verdict, spam handling, staleness). It is dense and long-ish for a single paragraph but wastes nothing.

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 must describe the return shape, and it does: per-token USD values, a risk verdict on the largest positions, a separate list for unrouteable tokens, a hidden-spam count, and a priceAsOf marker. An agent can interpret the response without further doc.

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, but the description adds meaning the schema doesn't: chain defaults are derived from address format (0x vs Solana), and it clarifies that 'all' expands to four EVM chains rather than everything. That resolves the only real ambiguity in the enum.

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?

Names a specific verb and resource ('every token a wallet holds, with USD values'), plus the exact chain scope and the address type it accepts. It is clearly distinct from siblings like token_quote or token_risk, which cover one token rather than a wallet's whole 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?

Explains the address/chain relationship explicitly ('all four EVM chains for a 0x address... or one chain with chain') so the agent knows how to constrain scope. It also routes the agent onward for deeper analysis ('run token_risk for the full check'), though it never states when not to use this tool.

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