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

Annotations already declare readOnly/openWorld/non-idempotent, and the description reinforces and enriches them: 'Reads or computes only and changes nothing' corroborates readOnlyHint, while 'each call is charged, so repeats are not free' plus 'first 25 free; failed calls free' explains why idempotentHint is false. It also discloses the pricing mechanism (x402 USDC or card key), which no annotation covers, and states the return shape (rating, reasons, AI summary) despite no output schema.

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?

Dense but front-loaded: what it does, what it returns, which chains, when to use it, and the billing model, in that order. Every clause carries information an agent needs, including the 'not investment advice' disclaimer and the example address, with no 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 steps in to describe the return values (rating tiers, reasons, AI summary) and the caveats that matter before calling (cost per call, free tier, Base-only flags). The only real gap is the absence of a boundary against the overlapping siblings contract_risk and token_report.

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 both parameters are already documented; the description adds genuine meaning on top: the chain default, the expanded network names, and the important constraint that risk flags are Base-only, which changes how an agent should interpret a non-Base result. The token parameter only gets an example address, adding little beyond the schema's ticker-or-address note.

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+resource (rug check on an ERC-20 token) and enumerates the artifact: a rating from fixed rules over honeypot/contract flags, liquidity, upgradeable proxy, and last-hour DEX buys/sells, plus reasons and an AI summary. It is distinguishable from generic siblings like price_token or token_supply, but it never explicitly contrasts itself with the close neighbors contract_risk, token_report or pack_token_analysis, so an agent still has to infer the boundary.

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 a concrete trigger ('Use before buying or accepting an unknown token') and a scoping caveat that risk flags exist on Base only, which steers chain selection. It stops short of naming an alternative or saying when NOT to use it (e.g. for tokens with deep liquidity or for held positions), so there is no explicit routing to a sibling.

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