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

Annotations only cover readOnly/openWorld; the description adds substantially more: the upstream data source (GoPlus) plus on-chain facts, the critical caveat that absence of flags is not a guarantee, and that the call is paid at 0.01 USDC per invocation. These are exactly the traits an agent cannot infer from structured fields.

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-loads the scope in the first clause, then the caveat, then the alternative, then the price. The parenthetical flag enumeration is dense but carries real information about return contents rather than 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?

With no output schema, the description still conveys what comes back (risk flags plus symbol/supply/owner facts) and what does not (verdict, liquidity). For a one-parameter paid read tool, nothing material is missing before invocation.

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% and the single parameter is already described in the schema as an ERC-20 contract address on Base. The description reinforces chain and token type but adds no new syntax or format constraints beyond that, so it sits just above the baseline.

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+resource+chain scope ('token risk flags ... for an ERC-20 on Base') and explicitly enumerates what is and is not returned. The sibling it is not (token-due-diligence) is named, so an agent can route without opening a schema.

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 an explicit scope limit ('ONLY'), an explicit exclusion ('No safety verdict'), and the condition that selects the alternative ('For a full check that ALSO adds contract/proxy facts and pool liquidity ... use token-due-diligence instead'). Also flags the cost precondition, which governs whether the call is appropriate at all.

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