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

Annotations only declare readOnlyHint and openWorldHint, yet the description adds substantial behavior the agent could not otherwise know: 3 free calls per day across all tools, $0.005 USDC via x402 or card credits paid in-band at params._meta["x402/payment"], and the exact upstream sources (GoPlus and DexScreener) with a note that every flag names its source field. These are real operational constraints that affect whether and how the agent should call it, with no contradiction of the annotations.

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 and mostly front-loaded, but the lead sentence is billing mechanics rather than the tool's purpose, and the trailing 'Not financial advice' plus repeated 'pass/warn/fail' phrasing are mild filler. Nearly every sentence still carries load.

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 two parameters resolved by the schema and an output schema already present, the description covers everything else an agent needs: cost and payment path, supported chains, evaluation groups, and data provenance. Nothing material is missing for correct 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 description coverage is 100% with a chain enum and a documented address format, so the baseline is 3. The description reinforces 'one ERC-20 token' and 'Base or Ethereum', which usefully bounds cardinality, but adds no format, default, or validation detail beyond the schema.

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 operation ('Rug pull check') on a specific resource ('one ERC-20 token') with a defined output contract: pass/warn/fail across honeypot signals, owner rights, liquidity and holder concentration, plus an overall rugRisk. The scope and the four evaluation groups separate it from generic siblings such as token_info or token_price without needing to open the 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?

Explicitly supplies a 'When to use' clause: new or unknown tokens, memecoins and snipes. That is a clear positive trigger, but it never names an alternative (e.g. token_risk or token_score) or states when this check is unnecessary, so the routing guidance is one-sided.

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