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

Annotations already declare read-only, idempotent, non-destructive, open-world, but the description adds real value beyond them: fail-closed semantics (unknown token returns UNKNOWN, never "safe"), the exact verdict taxonomy, the enumerated red-flag categories, and the $0.02 cost plus REST endpoint.

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-loaded with the framing question and verdict scale, then progressively adds call guidance, failure behavior, disclaimer, and endpoint. Dense but nearly every sentence carries information; the informal grade jargon and the advisory disclaimer are the only slightly soft parts.

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 an output schema present, the description needn't detail return structure, and it still previews the key fields. For a 2-param read-only screen, an agent has everything needed to decide to call it and interpret the result.

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 0%, so the description must carry the load and does: token is defined as an ERC-20 contract address on Base with the 0x... format, and amount_usd is defined as planned position size that scales expected_loss_usd — the latter explains the causal relationship the schema does not.

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 (safety check / verdict) and resource (Base ERC-20 token) and enumerates the exact outputs: grade, action, confidence, red flags, expected loss. Clearly distinct from siblings like mint_rug_check or check_wallet_reputation, which cover different assets/entities.

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?

"Call it before swapping into any Base token" gives an explicit trigger and ordering. It does not name alternatives or state when not to use it, but the Base-specific scope implicitly excludes the Solana/wallet/agent siblings.

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