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

Annotations declare readOnlyHint=true and openWorldHint=true, but the description adds substantial context beyond them: exactly which powers are inspected (mint, blacklist, pause, fee, proxy upgradeability, owner, DEX liquidity), that a real buy/sell is simulated, the return shape (verdict + 0-100 score + evidence), rate limits (3/day trial), and pricing ($0.01 USDC via x402). The simulation is clearly off-chain, so readOnlyHint is consistent, not contradicted.

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-loads the agent's actual decision ("Is this token safe to buy?") before the mechanics, then layers inputs, outputs, usage, trial, and price in a tight sequence. Every sentence carries operational value for an agent deciding whether and how to call it.

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 correctly supplies the return contract (verdict enum, 0-100 score, supporting evidence). Combined with the trial endpoint and x402 payment details, an agent has everything needed to invoke it, pay, and interpret results.

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 are already documented in the schema; the description only restates "Input: token address" and implies the simulation step without adding format or behavior nuance beyond the schema's own "Run the buy/sell simulation (default true)". Baseline 3 applies when the schema does the heavy lifting.

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?

Opens with a specific question that names the resource (Base token) and the exact risks it evaluates (honeypot, rug pull, scam), then states the mechanism: buy/sell simulation, tax measurement, mint/blacklist/pause/fee/proxy/liquidity checks. This clearly separates it from siblings like base_token (raw metadata) and base_token_risk_trial (the free trial variant).

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?

"Check before an agent trades a token" gives an explicit trigger condition, and the trial endpoint is named as a free alternative (3 calls/day). It stops short of stating when not to use it (e.g. non-Base chains, non-ERC-20 tokens) or how it relates to base_token_risk_trial by tool name rather than URL path.

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