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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond that — the per-chain checklist, the simulated $100 buy-then-sell through the router, the verdict scale (high/caution/low), and the 'not a guarantee' caveat. It stops short of saying whether the router test requires approvals, funds, or takes measurable time, and whether the verdict is deterministic per call.

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?

Opening sentence front-loads the question and the input, then the chain-specific checks are grouped logically and the return contract and caveat close it out. Dense but nearly every clause carries information; only the chain enumeration is mildly redundant with the enum.

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 only 2 parameters, no output schema, and minimal annotations, the description carries the burden well: it explains what is checked, what the output verdict looks like plus reasons, and the limits of the result. Nothing an agent needs to decide to call it, or to interpret the response, 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?

Schema description coverage is 100%, so both parameters (address as 0x or Solana mint, chain enum with documented defaults) are already fully explained structurally. The description only restates the supported chains, adding no format or edge-case detail beyond the schema, so the baseline 3 applies.

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: a pre-purchase risk assessment of a token by contract address, broken out per chain family (Solana mint/freeze/Token-2022/holder concentration; EVM taxes/ownership; both get a $100 round-trip test). This clearly separates it from token_quote and swap_quote, which price rather than diagnose.

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 title 'before you buy' plus 'What could go wrong buying a token' establishes the use case and timing precisely. It does not name alternative siblings (e.g., when to prefer token_quote for pricing) or state exclusions, so it falls short of a full when/when-not/alternatives statement.

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