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

With no annotations, the description carries the burden and does well: it discloses that findings come from bytecode inspection and Sourcify source verification, that a heuristic 0-100 score/grade is produced, and that liquidity is measured against the deepest Uniswap v3 pool. It omits operational traits an agent might need — latency, rate limits, cost, or whether unverified/no-pool tokens return partial results.

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 one-call aggregate value, then the payload contents, then the when-to-use. The long middle sentence is dense but every clause names a distinct data point an agent would otherwise have to source separately.

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 two-parameter read tool with an output schema, this is nearly complete — scope, payload, and usage trigger are all covered, and return values are enumerated even though the output schema already defines them. The remaining gap is input format (token address vs symbol, chain default), which matters for a tool whose whole premise is one-call simplicity.

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 description coverage is 0%, so the description must compensate, and it partially does: the five supported chains map onto the `chain` parameter's accepted values. However, it never says `chain` defaults to 'base', and it never clarifies whether `token` is a contract address or a symbol — the single most consequential ambiguity for calling this tool correctly.

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 and resource ('One-call due diligence on any ERC-20') and enumerates exactly what the report contains: safety score/grade, bytecode owner powers, proxy/ownership status, Sourcify verification, deployer, and deepest Uniswap v3 pool with price and depth. It also scopes the supported chains, so an agent can immediately tell this apart from narrow siblings like erc20_token_info or proxy_check.

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?

'Use before buying, listing or integrating a token' gives a clear triggering context, and 'Replaces about 6 separate calls' signals it is the aggregate option over the granular siblings. It stops short of naming those siblings (token_risk_check, uniswap_price, proxy_check, contract_info) or stating when NOT to use it, e.g. for non-EVM or non-listed tokens.

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